Machine Unlearning
Table of Contents
ICCV
ECCV
COLT
UAI
AISTATS
WACV
INFOCOM
DAC
IEEE Symposium on Security and Privacy
ALT
SIGMOD Conference
IEEE Trans. Pattern Anal. Mach. Intell.
IEEE Trans. Big Data
IEEE Trans. Emerg. Top. Comput. Intell.
ACM Trans. Intell. Syst. Technol.
Proc. VLDB Endow.
Nat. Mac. Intell.
Pattern Recognit.
Knowl. Based Syst.
Neural Networks
Neurocomputing
NeurIPS
Expand NeurIPS
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Certified Machine Unlearning via Noisy Stochastic Gradient Descent. | NeurIPS | 2024 | Link |
| Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning. | NeurIPS | 2024 | Link |
| Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable. | NeurIPS | 2024 | Link |
| Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models. | NeurIPS | 2024 | Link |
| Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement. | NeurIPS | 2024 | Link |
| UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models. | NeurIPS | 2024 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| Fast Model DeBias with Machine Unlearning. | NeurIPS | 2023 | Link |
| Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks. | NeurIPS | 2023 | Link |
| Model Sparsity Can Simplify Machine Unlearning. | NeurIPS | 2023 | Link |
| Towards Unbounded Machine Unlearning. | NeurIPS | 2023 | Link |
2022
| Title | Venue | Year | Link |
|---|---|---|---|
| Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization. | NeurIPS | 2022 | Link |
2021
| Title | Venue | Year | Link |
|---|---|---|---|
| Adaptive Machine Unlearning. | NeurIPS | 2021 | Link |
| Remember What You Want to Forget: Algorithms for Machine Unlearning. | NeurIPS | 2021 | Link |
ICML
Expand ICML
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning. | ICML | 2025 | Link |
| Leveraging Per-Instance Privacy for Machine Unlearning. | ICML | 2025 | Link |
| NegMerge: Sign-Consensual Weight Merging for Machine Unlearning. | ICML | 2025 | Link |
| SEMU: Singular Value Decomposition for Efficient Machine Unlearning. | ICML | 2025 | Link |
| When to Forget? Complexity Trade-offs in Machine Unlearning. | ICML | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Verification of Machine Unlearning is Fragile. | ICML | 2024 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| Fast Federated Machine Unlearning with Nonlinear Functional Theory. | ICML | 2023 | Link |
| Forget Unlearning: Towards True Data-Deletion in Machine Learning. | ICML | 2023 | Link |
| From Adaptive Query Release to Machine Unlearning. | ICML | 2023 | Link |
2021
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning for Random Forests. | ICML | 2021 | Link |
ICLR
Expand ICLR
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| A Closer Look at Machine Unlearning for Large Language Models. | ICLR | 2025 | Link |
| Adversarial Machine Unlearning. | ICLR | 2025 | Link |
| DynFrs: An Efficient Framework for Machine Unlearning in Random Forest. | ICLR | 2025 | Link |
| MUSE: Machine Unlearning Six-Way Evaluation for Language Models. | ICLR | 2025 | Link |
| Machine Unlearning Fails to Remove Data Poisoning Attacks. | ICLR | 2025 | Link |
| Machine Unlearning via Simulated Oracle Matching. | ICLR | 2025 | Link |
| Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models. | ICLR | 2025 | Link |
| The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning. | ICLR | 2025 | Link |
| Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning. | ICLR | 2025 | Link |
| Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy. | ICLR | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning for Image-to-Image Generative Models. | ICLR | 2024 | Link |
| SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation. | ICLR | 2024 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning of Federated Clusters. | ICLR | 2023 | Link |
NDSS
Expand NDSS
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services. | NDSS | 2024 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning of Features and Labels. | NDSS | 2023 | Link |
CVPR
Expand CVPR
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty. | CVPR | 2025 | Link |
| The Illusion of Unlearning: The Unstable Nature of Machine Unlearning in Text-to-Image Diffusion Models. | CVPR | 2025 | Link |
| Towards Source-Free Machine Unlearning. | CVPR | 2025 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer. | CVPR | 2023 | Link |
ICCV
Expand ICCV
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| MUter: Machine Unlearning on Adversarially Trained Models. | ICCV | 2023 | Link |
| SAFE: Machine Unlearning With Shard Graphs. | ICCV | 2023 | Link |
ECCV
Expand ECCV
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning. | ECCV | 2024 | Link |
| Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-of-Distribution Images. | ECCV | 2024 | Link |
| Learning to Unlearn for Robust Machine Unlearning. | ECCV | 2024 | Link |
| MultiDelete for Multimodal Machine Unlearning. | ECCV | 2024 | Link |
COLT
UAI
Expand UAI
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| SALSA: A Secure, Adaptive and Label-Agnostic Scalable Algorithm for Machine Unlearning. | UAI | 2025 | Link |
IJCAI
Expand IJCAI
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Contrastive Unlearning: A Contrastive Approach to Machine Unlearning. | IJCAI | 2025 | Link |
| How to Make Reproducible Research in Machine Unlearning with ERASURE. | IJCAI | 2025 | Link |
| Zero-Shot Machine Unlearning with Proxy Adversarial Data Generation. | IJCAI | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning via Null Space Calibration. | IJCAI | 2024 | Link |
| Machine Unlearning: Challenges in Data Quality and Access. | IJCAI | 2024 | Link |
| Unlearning during Learning: An Efficient Federated Machine Unlearning Method. | IJCAI | 2024 | Link |
2022
| Title | Venue | Year | Link |
|---|---|---|---|
| ARCANE: An Efficient Architecture for Exact Machine Unlearning. | IJCAI | 2022 | Link |
AAAI
Expand AAAI
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting. | AAAI | 2025 | Link |
| Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage. | AAAI | 2025 | Link |
| SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness. | AAAI | 2025 | Link |
| Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models. | AAAI | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Backdoor Attacks via Machine Unlearning. | AAAI | 2024 | Link |
| Fast Machine Unlearning without Retraining through Selective Synaptic Dampening. | AAAI | 2024 | Link |
| Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation. | AAAI | 2024 | Link |
2022
| Title | Venue | Year | Link |
|---|---|---|---|
| Hard to Forget: Poisoning Attacks on Certified Machine Unlearning. | AAAI | 2022 | Link |
AISTATS
Expand AISTATS
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Fair Machine Unlearning: Data Removal while Mitigating Disparities. | AISTATS | 2024 | Link |
KDD
Expand KDD
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| From Expansion to Retraction: Long-tailed Machine Unlearning via Boundary Manipulation. | KDD | 2025 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning in Gradient Boosting Decision Trees. | KDD | 2023 | Link |
CCS
Expand CCS
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Prototype Surgery: Tailoring Neural Prototypes via Soft Labels for Efficient Machine Unlearning. | CCS | 2025 | Link |
| Rethinking Machine Unlearning in Image Generation Models. | CCS | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach. | CCS | 2024 | Link |
2021
| Title | Venue | Year | Link |
|---|---|---|---|
| When Machine Unlearning Jeopardizes Privacy. | CCS | 2021 | Link |
ACL
Expand ACL
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Decoupling Memories, Muting Neurons: Towards Practical Machine Unlearning for Large Language Models. | ACL | 2025 | Link |
| Disentangling Biased Knowledge from Reasoning in Large Language Models via Machine Unlearning. | ACL | 2025 | Link |
| MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models. | ACL | 2025 | Link |
| SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning. | ACL | 2025 | Link |
| Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation. | ACL | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning. | ACL | 2024 | Link |
| Machine Unlearning of Pre-trained Large Language Models. | ACL | 2024 | Link |
| Towards Safer Large Language Models through Machine Unlearning. | ACL | 2024 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment. | ACL | 2023 | Link |
EMNLP
Expand EMNLP
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models. | EMNLP | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Can Machine Unlearning Reduce Social Bias in Language Models? | EMNLP | 2024 | Link |
| Rethinking Evaluation Methods for Machine Unlearning. | EMNLP | 2024 | Link |
WACV
Expand WACV
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Revisiting Machine Unlearning with Dimensional Alignment. | WACV | 2025 | Link |
INFOCOM
Expand INFOCOM
2022
| Title | Venue | Year | Link |
|---|---|---|---|
| Backdoor Defense with Machine Unlearning. | INFOCOM | 2022 | Link |
WWW
Expand WWW
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| FUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary Unlearning. | WWW | 2025 | Link |
| Fairness and Robustness in Machine Unlearning. | WWW | 2025 | Link |
| TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning. | WWW | 2025 | Link |
| Towards Safe Machine Unlearning: A Paradigm that Mitigates Performance Degradation. | WWW | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Breaking the Trilemma of Privacy, Utility, and Efficiency via Controllable Machine Unlearning. | WWW | 2024 | Link |
DAC
Expand DAC
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning. | DAC | 2025 | Link |
SP
Expand SP
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning. | SP | 2024 | Link |
2021
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning. | SP | 2021 | Link |
IEEE Symposium on Security and Privacy
Expand IEEE Symposium on Security and Privacy
2015
| Title | Venue | Year | Link |
|---|---|---|---|
| Towards Making Systems Forget with Machine Unlearning. | IEEE Symposium on Security and Privacy | 2015 | Link |
USENIX Security Symposium
Expand USENIX Security Symposium
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning. | USENIX Security Symposium | 2025 | Link |
| Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective. | USENIX Security Symposium | 2025 | Link |
2022
| Title | Venue | Year | Link |
|---|---|---|---|
| On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning. | USENIX Security Symposium | 2022 | Link |
ACM Multimedia
Expand ACM Multimedia
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| GDR-GMA: Machine Unlearning via Direction-Rectified and Magnitude-Adjusted Gradients. | ACM Multimedia | 2024 | Link |
2022
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning for Image Retrieval: A Generative Scrubbing Approach. | ACM Multimedia | 2022 | Link |
ALT
Expand ALT
2021
| Title | Venue | Year | Link |
|---|---|---|---|
| Descent-to-Delete: Gradient-Based Methods for Machine Unlearning. | ALT | 2021 | Link |
Proc. ACM Manag. Data
Expand Proc. ACM Manag. Data
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning in Learned Databases: An Experimental Analysis. | Proc. ACM Manag. Data | 2024 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| DeltaBoost: Gradient Boosting Decision Trees with Efficient Machine Unlearning. | Proc. ACM Manag. Data | 2023 | Link |
SIGMOD Conference
Expand SIGMOD Conference
2021
| Title | Venue | Year | Link |
|---|---|---|---|
| HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning. | SIGMOD Conference | 2021 | Link |
CIKM
Expand CIKM
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| ERASURE: A Modular and Extensible Framework for Machine Unlearning. | CIKM | 2025 | Link |
| Enabling Group Fairness in Machine Unlearning via Distribution Correction. | CIKM | 2025 | Link |
| MU-OT: Effective and Unified Machine Unlearning with Optimal Transport for Feature Realignment. | CIKM | 2025 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| Closed-form Machine Unlearning for Matrix Factorization. | CIKM | 2023 | Link |
Mach. Learn.
Expand Mach. Learn.
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| MUSO: achieving exact machine unlearning in over-parameterized regimes. | Mach. Learn. | 2025 | Link |
2022
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine unlearning: linear filtration for logit-based classifiers. | Mach. Learn. | 2022 | Link |
IEEE Trans. Pattern Anal. Mach. Intell.
Expand IEEE Trans. Pattern Anal. Mach. Intell.
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Towards Natural Machine Unlearning. | IEEE Trans. Pattern Anal. Mach. Intell. | 2025 | Link |
IEEE Trans. Neural Networks Learn. Syst.
Expand IEEE Trans. Neural Networks Learn. Syst.
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy. | IEEE Trans. Neural Networks Learn. Syst. | 2025 | Link |
| Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects. | IEEE Trans. Neural Networks Learn. Syst. | 2025 | Link |
| Toward Efficient Target-Level Machine Unlearning Based on Essential Graph. | IEEE Trans. Neural Networks Learn. Syst. | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Fast Yet Effective Machine Unlearning. | IEEE Trans. Neural Networks Learn. Syst. | 2024 | Link |
IEEE Trans. Knowl. Data Eng.
Expand IEEE Trans. Knowl. Data Eng.
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| FELEMN: Toward Efficient Feature-Level Machine Unlearning for Exact Privacy Protection. | IEEE Trans. Knowl. Data Eng. | 2025 | Link |
| Machine Unlearning Through Fine-Grained Model Parameters Perturbation. | IEEE Trans. Knowl. Data Eng. | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| FRAMU: Attention-Based Machine Unlearning Using Federated Reinforcement Learning. | IEEE Trans. Knowl. Data Eng. | 2024 | Link |
IEEE Trans. Big Data
Expand IEEE Trans. Big Data
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation. | IEEE Trans. Big Data | 2025 | Link |
IEEE Trans. Emerg. Top. Comput. Intell.
Expand IEEE Trans. Emerg. Top. Comput. Intell.
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning: Solutions and Challenges. | IEEE Trans. Emerg. Top. Comput. Intell. | 2024 | Link |
IEEE Trans. Inf. Forensics Secur.
Expand IEEE Trans. Inf. Forensics Secur.
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Evaluation of Machine Unlearning Through Model Difference. | IEEE Trans. Inf. Forensics Secur. | 2025 | Link |
| Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakage. | IEEE Trans. Inf. Forensics Secur. | 2025 | Link |
| SCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications. | IEEE Trans. Inf. Forensics Secur. | 2025 | Link |
| TruVRF: Toward Triple-Granularity Verification on Machine Unlearning. | IEEE Trans. Inf. Forensics Secur. | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning via Representation Forgetting With Parameter Self-Sharing. | IEEE Trans. Inf. Forensics Secur. | 2024 | Link |
| Verifying in the Dark: Verifiable Machine Unlearning by Using Invisible Backdoor Triggers. | IEEE Trans. Inf. Forensics Secur. | 2024 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| FedRecovery: Differentially Private Machine Unlearning for Federated Learning Frameworks. | IEEE Trans. Inf. Forensics Secur. | 2023 | Link |
| Zero-Shot Machine Unlearning. | IEEE Trans. Inf. Forensics Secur. | 2023 | Link |
ACM Trans. Intell. Syst. Technol.
Expand ACM Trans. Intell. Syst. Technol.
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| A Survey of Machine Unlearning. | ACM Trans. Intell. Syst. Technol. | 2025 | Link |
Proc. VLDB Endow.
Expand Proc. VLDB Endow.
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Snapcase - Regain Control over Your Predictions with Low-Latency Machine Unlearning. | Proc. VLDB Endow. | 2024 | Link |
Nat. Mac. Intell.
Expand Nat. Mac. Intell.
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Rethinking machine unlearning for large language models. | Nat. Mac. Intell. | 2025 | Link |
Pattern Recognit.
Expand Pattern Recognit.
2026
| Title | Venue | Year | Link |
|---|---|---|---|
| Preserving privacy without compromising accuracy: Machine unlearning for handwritten text recognition. | Pattern Recognit. | 2026 | Link |
Knowl. Based Syst.
Expand Knowl. Based Syst.
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| Defending against gradient inversion attacks in federated learning via statistical machine unlearning. | Knowl. Based Syst. | 2024 | Link |
Neural Networks
Expand Neural Networks
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| Fast yet versatile machine unlearning for deep neural networks. | Neural Networks | 2025 | Link |
Neurocomputing
Expand Neurocomputing
2026
| Title | Venue | Year | Link |
|---|---|---|---|
| How secure is forgetting? Linking machine unlearning to machine learning attacks. | Neurocomputing | 2026 | Link |
arXiv
Expand arXiv
2026
| Title | Venue | Year | Link |
|---|---|---|---|
| A Robust Certified Machine Unlearning Method Under Distribution Shift | arXiv | 2026 | Link |
| Adaptively Robust Resettable Streaming | arXiv | 2026 | Link |
| Agentic Unlearning: When LLM Agent Meets Machine Unlearning | arXiv | 2026 | Link |
| Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning | arXiv | 2026 | Link |
| Benchmarking Unlearning for Vision Transformers | arXiv | 2026 | Link |
| Certified Per-Instance Unlearning Using Individual Sensitivity Bounds | arXiv | 2026 | Link |
| Critic-Guided Reinforcement Unlearning in Text-to-Image Diffusion | arXiv | 2026 | Link |
| Distribution-Guided and Constrained Quantum Machine Unlearning | arXiv | 2026 | Link |
| Don't Break the Boundary: Continual Unlearning for OOD Detection Based on Free Energy Repulsion | arXiv | 2026 | Link |
| EVE: Efficient Verification of Data Erasure through Customized Perturbation in Approximate Unlearning | arXiv | 2026 | Link |
| Easy Data Unlearning Bench | arXiv | 2026 | Link |
| Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias | arXiv | 2026 | Link |
| Erase at the Core: Representation Unlearning for Machine Unlearning | arXiv | 2026 | Link |
| EvoMU: Evolutionary Machine Unlearning | arXiv | 2026 | Link |
| FADE: Selective Forgetting via Sparse LoRA and Self-Distillation | arXiv | 2026 | Link |
| FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning | arXiv | 2026 | Link |
| Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models | arXiv | 2026 | Link |
| Forget by Uncertainty: Orthogonal Entropy Unlearning for Quantized Neural Networks | arXiv | 2026 | Link |
| Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking | arXiv | 2026 | Link |
| Forgetting Similar Samples: Can Machine Unlearning Do it Better? | arXiv | 2026 | Link |
| GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints | arXiv | 2026 | Link |
| GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning | arXiv | 2026 | Link |
| Governing AI Forgetting: Auditing for Machine Unlearning Compliance | arXiv | 2026 | Link |
| Inference-time Unlearning Using Conformal Prediction | arXiv | 2026 | Link |
| Is Gradient Ascent Really Necessary? Memorize to Forget for Machine Unlearning | arXiv | 2026 | Link |
| JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification | arXiv | 2026 | Link |
| LEGATO: Good Identity Unlearning Is Continuous | arXiv | 2026 | Link |
| Layer-Targeted Multilingual Knowledge Erasure in Large Language Models | arXiv | 2026 | Link |
| Machine Unlearning and Continual Learning in Hybrid Resistive Memory Neuromorphic Systems | arXiv | 2026 | Link |
| MeGU: Machine-Guided Unlearning with Target Feature Disentanglement | arXiv | 2026 | Link |
| Memory Retrieval in Transformers: Insights from The Encoding Specificity Principle | arXiv | 2026 | Link |
| Memory Undone: Between Knowing and Not Knowing in Data Systems | arXiv | 2026 | Link |
| Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs | arXiv | 2026 | Link |
| Protecting the Undeleted in Machine Unlearning | arXiv | 2026 | Link |
| QUAIL: Quantization Aware Unlearning for Mitigating Misinformation in LLMs | arXiv | 2026 | Link |
| REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation Loop | arXiv | 2026 | Link |
| ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models | arXiv | 2026 | Link |
| Regularized $f$-Divergence Kernel Tests | arXiv | 2026 | Link |
| Representation Unlearning: Forgetting through Information Compression | arXiv | 2026 | Link |
| Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures | arXiv | 2026 | Link |
| SafeMo: Linguistically Grounded Unlearning for Trustworthy Text-to-Motion Generation | arXiv | 2026 | Link |
| Sparsity-Aware Unlearning for Large Language Models | arXiv | 2026 | Link |
| Statistical Roughness-Informed Machine Unlearning | arXiv | 2026 | Link |
| Suppression or Deletion: A Restoration-Based Representation-Level Analysis of Machine Unlearning | arXiv | 2026 | Link |
| Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance | arXiv | 2026 | Link |
| The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples | arXiv | 2026 | Link |
| Toward Understanding Unlearning Difficulty: A Mechanistic Perspective and Circuit-Guided Difficulty Metric | arXiv | 2026 | Link |
| Towards Fair Large Language Model-based Recommender Systems without Costly Retraining | arXiv | 2026 | Link |
| UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning | arXiv | 2026 | Link |
| UnPII: Unlearning Personally Identifiable Information with Quantifiable Exposure Risk | arXiv | 2026 | Link |
| Unintended Memorization of Sensitive Information in Fine-Tuned Language Models | arXiv | 2026 | Link |
| UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion | arXiv | 2026 | Link |
| Unlearning Noise in PINNs: A Selective Pruning Framework for PDE Inverse Problems | arXiv | 2026 | Link |
| Unlearning in LLMs: Methods, Evaluation, and Open Challenges | arXiv | 2026 | Link |
| Variance-Reduced $(\varepsilon,δ)-$Unlearning using Forget Set Gradients | arXiv | 2026 | Link |
| Why Some Models Resist Unlearning: A Linear Stability Perspective | arXiv | 2026 | Link |
2025
| Title | Venue | Year | Link |
|---|---|---|---|
| "Alexa, can you forget me?" Machine Unlearning Benchmark in Spoken Language Understanding | arXiv | 2025 | Link |
| A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction | arXiv | 2025 | Link |
| A Survey on Unlearnable Data | arXiv | 2025 | Link |
| A Unified Framework for Diffusion Model Unlearning with f-Divergence | arXiv | 2025 | Link |
| A Unified Gradient-based Framework for Task-agnostic Continual Learning-Unlearning | arXiv | 2025 | Link |
| AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models | arXiv | 2025 | Link |
| Abstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential Privacy | arXiv | 2025 | Link |
| Adaptive-lambda Subtracted Importance Sampled Scores in Machine Unlearning for DDPMs and VAEs | arXiv | 2025 | Link |
| Adversarial Mixup Unlearning | arXiv | 2025 | Link |
| Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race | arXiv | 2025 | Link |
| An Unlearning Framework for Continual Learning | arXiv | 2025 | Link |
| Analise de Desaprendizado de Maquina em Modelos de Classificacao de Imagens Medicas | arXiv | 2025 | Link |
| Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols | arXiv | 2025 | Link |
| Ascent Fails to Forget | arXiv | 2025 | Link |
| Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge | arXiv | 2025 | Link |
| Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion | arXiv | 2025 | Link |
| Beyond Uniform Deletion: A Data Value-Weighted Framework for Certified Machine Unlearning | arXiv | 2025 | Link |
| Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting | arXiv | 2025 | Link |
| CUFG: Curriculum Unlearning Guided by the Forgetting Gradient | arXiv | 2025 | Link |
| CURE: Centroid-guided Unsupervised Representation Erasure for Facial Recognition Systems | arXiv | 2025 | Link |
| Causal Fuzzing for Verifying Machine Unlearning | arXiv | 2025 | Link |
| Certified Data Removal Under High-dimensional Settings | arXiv | 2025 | Link |
| Certified Unlearning for Neural Networks | arXiv | 2025 | Link |
| CoUn: Empowering Machine Unlearning via Contrastive Learning | arXiv | 2025 | Link |
| Conformal Unlearning: A New Paradigm for Unlearning in Conformal Predictors | arXiv | 2025 | Link |
| Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective | arXiv | 2025 | Link |
| ContinualFlow: Learning and Unlearning with Neural Flow Matching | arXiv | 2025 | Link |
| Controllable Machine Unlearning via Gradient Pivoting | arXiv | 2025 | Link |
| Cross-Modal Attention Guided Unlearning in Vision-Language Models | arXiv | 2025 | Link |
| DUSK: Do Not Unlearn Shared Knowledge | arXiv | 2025 | Link |
| Data Augmentation Improves Machine Unlearning | arXiv | 2025 | Link |
| Data Unlearning in Diffusion Models | arXiv | 2025 | Link |
| Deep Contrastive Unlearning for Language Models | arXiv | 2025 | Link |
| Delete and Retain: Efficient Unlearning for Document Classification | arXiv | 2025 | Link |
| Descend or Rewind? Stochastic Gradient Descent Unlearning | arXiv | 2025 | Link |
| Distill, Forget, Repeat: A Framework for Continual Unlearning in Text-to-Image Diffusion Models | arXiv | 2025 | Link |
| Distributional Machine Unlearning via Selective Data Removal | arXiv | 2025 | Link |
| Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness | arXiv | 2025 | Link |
| Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech | arXiv | 2025 | Link |
| Does Machine Unlearning Truly Remove Knowledge? | arXiv | 2025 | Link |
| DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers | arXiv | 2025 | Link |
| Efficient Knowledge Graph Unlearning with Zeroth-order Information | arXiv | 2025 | Link |
| Efficient Machine Unlearning by Model Splitting and Core Sample Selection | arXiv | 2025 | Link |
| Efficient Machine Unlearning via Influence Approximation | arXiv | 2025 | Link |
| Efficient Unlearning with Privacy Guarantees | arXiv | 2025 | Link |
| Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery | arXiv | 2025 | Link |
| Efficient Verified Machine Unlearning For Distillation | arXiv | 2025 | Link |
| Erased but Not Forgotten: How Backdoors Compromise Concept Erasure | arXiv | 2025 | Link |
| Exploring Incremental Unlearning: Techniques, Challenges, and Future Directions | arXiv | 2025 | Link |
| FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model | arXiv | 2025 | Link |
| FAME: Fictional Actors for Multilingual Erasure | arXiv | 2025 | Link |
| FROC: A Unified Framework with Risk-Optimized Control for Machine Unlearning in LLMs | arXiv | 2025 | Link |
| FROG: Fair Removal on Graphs | arXiv | 2025 | Link |
| FUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary Unlearning | arXiv | 2025 | Link |
| Face Identity Unlearning for Retrieval via Embedding Dispersion | arXiv | 2025 | Link |
| Few-Shot Concept Unlearning with Low Rank Adaptation | arXiv | 2025 | Link |
| FiCABU: A Fisher-Based, Context-Adaptive Machine Unlearning Processor for Edge AI | arXiv | 2025 | Link |
| Forgetting by Pruning: Data Deletion in Join Cardinality Estimation | arXiv | 2025 | Link |
| Gaussian Certified Unlearning in High Dimensions: A Hypothesis Testing Approach | arXiv | 2025 | Link |
| Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization | arXiv | 2025 | Link |
| Grokked Models are Better Unlearners | arXiv | 2025 | Link |
| Group-robust Machine Unlearning | arXiv | 2025 | Link |
| Hierarchy-Aware Multimodal Unlearning for Medical AI | arXiv | 2025 | Link |
| How Does Overparameterization Affect Machine Unlearning of Deep Neural Networks? | arXiv | 2025 | Link |
| Hubble: a Model Suite to Advance the Study of LLM Memorization | arXiv | 2025 | Link |
| Illuminating the Black Box: Real-Time Monitoring of Backdoor Unlearning in CNNs via Explainable AI | arXiv | 2025 | Link |
| Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning | arXiv | 2025 | Link |
| Improving Unlearning with Model Updates Probably Aligned with Gradients | arXiv | 2025 | Link |
| Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning | arXiv | 2025 | Link |
| Investigating Model Editing for Unlearning in Large Language Models | arXiv | 2025 | Link |
| Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design | arXiv | 2025 | Link |
| KnowledgeSmith: Uncovering Knowledge Updating in LLMs with Model Editing and Unlearning | arXiv | 2025 | Link |
| Layered Unlearning for Adversarial Relearning | arXiv | 2025 | Link |
| Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning | arXiv | 2025 | Link |
| LetheViT: Selective Machine Unlearning for Vision Transformers via Attention-Guided Contrastive Learning | arXiv | 2025 | Link |
| Leveraging Distribution Matching to Make Approximate Machine Unlearning Faster | arXiv | 2025 | Link |
| Leveraging Per-Instance Privacy for Machine Unlearning | arXiv | 2025 | Link |
| Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models | arXiv | 2025 | Link |
| LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning | arXiv | 2025 | Link |
| LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty | arXiv | 2025 | Link |
| Losing is for Cherishing: Data Valuation Based on Machine Unlearning and Shapley Value | arXiv | 2025 | Link |
| MCU: Improving Machine Unlearning through Mode Connectivity | arXiv | 2025 | Link |
| MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models | arXiv | 2025 | Link |
| MPRU: Modular Projection-Redistribution Unlearning as Output Filter for Classification Pipelines | arXiv | 2025 | Link |
| MRD-LiNet: A Novel Lightweight Hybrid CNN with Gradient-Guided Unlearning for Improved Drought Stress Identification | arXiv | 2025 | Link |
| MUBox: A Critical Evaluation Framework of Deep Machine Unlearning | arXiv | 2025 | Link |
| Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs | arXiv | 2025 | Link |
| Machine Unlearning for Responsible and Adaptive AI in Education | arXiv | 2025 | Link |
| Machine Unlearning for Robust DNNs: Attribution-Guided Partitioning and Neuron Pruning in Noisy Environments | arXiv | 2025 | Link |
| Machine Unlearning for Streaming Forgetting | arXiv | 2025 | Link |
| Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU | arXiv | 2025 | Link |
| Machine Unlearning in Speech Emotion Recognition via Forget Set Alone | arXiv | 2025 | Link |
| Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study | arXiv | 2025 | Link |
| Machine Unlearning of Traffic State Estimation and Prediction | arXiv | 2025 | Link |
| Machine Unlearning under Overparameterization | arXiv | 2025 | Link |
| Machine Unlearning via Information Theoretic Regularization | arXiv | 2025 | Link |
| Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models | arXiv | 2025 | Link |
| Memory-Efficient Distributed Unlearning | arXiv | 2025 | Link |
| Mirror Mirror on the Wall, Have I Forgotten it All? A New Framework for Evaluating Machine Unlearning | arXiv | 2025 | Link |
| Mo' Memory, Mo' Problems: Stream-Native Machine Unlearning | arXiv | 2025 | Link |
| MobText-SISA: Efficient Machine Unlearning for Mobility Logs with Spatio-Temporal and Natural-Language Data | arXiv | 2025 | Link |
| Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs | arXiv | 2025 | Link |
| Module-Aware Parameter-Efficient Machine Unlearning on Transformers | arXiv | 2025 | Link |
| Mr. Snuffleupagus at SemEval-2025 Task 4: Unlearning Factual Knowledge from LLMs Using Adaptive RMU | arXiv | 2025 | Link |
| No Encore: Unlearning as Opt-Out in Music Generation | arXiv | 2025 | Link |
| Node-level Contrastive Unlearning on Graph Neural Networks | arXiv | 2025 | Link |
| OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Models | arXiv | 2025 | Link |
| OFMU: Optimization-Driven Framework for Machine Unlearning | arXiv | 2025 | Link |
| On the Impossibility of Retrain Equivalence in Machine Unlearning | arXiv | 2025 | Link |
| On the limitation of evaluating machine unlearning using only a single training seed | arXiv | 2025 | Link |
| Online Gradient Boosting Decision Tree: In-Place Updates for Efficient Adding/Deleting Data | arXiv | 2025 | Link |
| Open Problems in Machine Unlearning for AI Safety | arXiv | 2025 | Link |
| OpenGU: A Comprehensive Benchmark for Graph Unlearning | arXiv | 2025 | Link |
| PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning | arXiv | 2025 | Link |
| PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models | arXiv | 2025 | Link |
| POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse | arXiv | 2025 | Link |
| Position: Bridge the Gaps between Machine Unlearning and AI Regulation | arXiv | 2025 | Link |
| Privacy Preservation through Practical Machine Unlearning | arXiv | 2025 | Link |
| Privacy-Aware Lifelong Learning | arXiv | 2025 | Link |
| Probing Knowledge Holes in Unlearned LLMs | arXiv | 2025 | Link |
| Probing then Editing: A Push-Pull Framework for Retain-Free Machine Unlearning in Industrial IoT | arXiv | 2025 | Link |
| Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods | arXiv | 2025 | Link |
| Prompting Forgetting: Unlearning in GANs via Textual Guidance | arXiv | 2025 | Link |
| Protecting the Neural Networks against FGSM Attack Using Machine Unlearning | arXiv | 2025 | Link |
| Provable Unlearning with Gradient Ascent on Two-Layer ReLU Neural Networks | arXiv | 2025 | Link |
| Quantifying Cross-Modality Memorization in Vision-Language Models | arXiv | 2025 | Link |
| Quotation-Based Data Retention Mechanism for Data Privacy in LLM-Empowered Network Services | arXiv | 2025 | Link |
| ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning | arXiv | 2025 | Link |
| Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness | arXiv | 2025 | Link |
| Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention | arXiv | 2025 | Link |
| Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy | arXiv | 2025 | Link |
| Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data | arXiv | 2025 | Link |
| Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection | arXiv | 2025 | Link |
| Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy | arXiv | 2025 | Link |
| Revisiting the Past: Data Unlearning with Model State History | arXiv | 2025 | Link |
| Robust MLLM Unlearning via Visual Knowledge Distillation | arXiv | 2025 | Link |
| Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels | arXiv | 2025 | Link |
| Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space | arXiv | 2025 | Link |
| SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs | arXiv | 2025 | Link |
| SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design | arXiv | 2025 | Link |
| SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders | arXiv | 2025 | Link |
| SCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications | arXiv | 2025 | Link |
| SEMU: Singular Value Decomposition for Efficient Machine Unlearning | arXiv | 2025 | Link |
| SEPS: A Separability Measure for Robust Unlearning in LLMs | arXiv | 2025 | Link |
| SHA256 at SemEval-2025 Task 4: Selective Amnesia -- Constrained Unlearning for Large Language Models via Knowledge Isolation | arXiv | 2025 | Link |
| SIMU: Selective Influence Machine Unlearning | arXiv | 2025 | Link |
| SMS: Self-supervised Model Seeding for Verification of Machine Unlearning | arXiv | 2025 | Link |
| SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning | arXiv | 2025 | Link |
| Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning | arXiv | 2025 | Link |
| Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning | arXiv | 2025 | Link |
| Selective Forgetting in Option Calibration: An Operator-Theoretic Gauss-Newton Framework | arXiv | 2025 | Link |
| Sharpness-Aware Parameter Selection for Machine Unlearning | arXiv | 2025 | Link |
| SineProject: Machine Unlearning for Stable Vision Language Alignment | arXiv | 2025 | Link |
| Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models | arXiv | 2025 | Link |
| Soft Weighted Machine Unlearning | arXiv | 2025 | Link |
| Speech Unlearning | arXiv | 2025 | Link |
| Stable Forgetting: Bounded Parameter-Efficient Unlearning in LLMs | arXiv | 2025 | Link |
| Stress-Testing Causal Claims via Cardinality Repairs | arXiv | 2025 | Link |
| Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic | arXiv | 2025 | Link |
| Superior resilience to poisoning and amenability to unlearning in quantum machine learning | arXiv | 2025 | Link |
| Supervised Contrastive Machine Unlearning of Background Bias in Sonar Image Classification with Fine-Grained Explainable AI | arXiv | 2025 | Link |
| Synthetic Forgetting without Access: A Few-shot Zero-glance Framework for Machine Unlearning | arXiv | 2025 | Link |
| System-Aware Unlearning Algorithms: Use Lesser, Forget Faster | arXiv | 2025 | Link |
| TAIJI: MCP-based Multi-Modal Data Analytics on Data Lakes | arXiv | 2025 | Link |
| TAPE: Tailored Posterior Difference for Auditing of Machine Unlearning | arXiv | 2025 | Link |
| Targeted Unlearning Using Perturbed Sign Gradient Methods With Applications On Medical Images | arXiv | 2025 | Link |
| Teleportation-Based Defenses for Privacy in Approximate Machine Unlearning | arXiv | 2025 | Link |
| The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation | arXiv | 2025 | Link |
| The Measure of Deception: An Analysis of Data Forging in Machine Unlearning | arXiv | 2025 | Link |
| The Space Complexity of Learning-Unlearning Algorithms | arXiv | 2025 | Link |
| Toward Scalable Graph Unlearning: A Node Influence Maximization based Approach | arXiv | 2025 | Link |
| Towards Aligned Data Forgetting via Twin Machine Unlearning | arXiv | 2025 | Link |
| Towards Irreversible Machine Unlearning for Diffusion Models | arXiv | 2025 | Link |
| Towards Machine Unlearning for Paralinguistic Speech Processing | arXiv | 2025 | Link |
| Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models | arXiv | 2025 | Link |
| Towards Reliable Forgetting: A Survey on Machine Unlearning Verification | arXiv | 2025 | Link |
| Towards Source-Free Machine Unlearning | arXiv | 2025 | Link |
| Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgotten | arXiv | 2025 | Link |
| Towards a Real-World Aligned Benchmark for Unlearning in Recommender Systems | arXiv | 2025 | Link |
| UCD: Unlearning in LLMs via Contrastive Decoding | arXiv | 2025 | Link |
| UnGuide: Learning to Forget with LoRA-Guided Diffusion Models | arXiv | 2025 | Link |
| Understanding Machine Unlearning Through the Lens of Mode Connectivity | arXiv | 2025 | Link |
| Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation | arXiv | 2025 | Link |
| Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs | arXiv | 2025 | Link |
| Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack | arXiv | 2025 | Link |
| Unlearning-Enhanced Website Fingerprinting Attack: Against Backdoor Poisoning in Anonymous Networks | arXiv | 2025 | Link |
| Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI | arXiv | 2025 | Link |
| Variational Diffusion Unlearning: A Variational Inference Framework for Unlearning in Diffusion Models under Data Constraints | arXiv | 2025 | Link |
| Verifiable Unlearning on Edge | arXiv | 2025 | Link |
| Verifying Robust Unlearning: Probing Residual Knowledge in Unlearned Models | arXiv | 2025 | Link |
| Video Unlearning via Low-Rank Refusal Vector | arXiv | 2025 | Link |
| WSS-CL: Weight Saliency Soft-Guided Contrastive Learning for Efficient Machine Unlearning Image Classification | arXiv | 2025 | Link |
| What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests | arXiv | 2025 | Link |
| When Forgetting Triggers Backdoors: A Clean Unlearning Attack | arXiv | 2025 | Link |
| When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers | arXiv | 2025 | Link |
| When to Forget? Complexity Trade-offs in Machine Unlearning | arXiv | 2025 | Link |
| ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models | arXiv | 2025 | Link |
| ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs | arXiv | 2025 | Link |
| iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning loss | arXiv | 2025 | Link |
| zkUnlearner: A Zero-Knowledge Framework for Verifiable Unlearning with Multi-Granularity and Forgery-Resistance | arXiv | 2025 | Link |
2024
| Title | Venue | Year | Link |
|---|---|---|---|
| A Comparative Study of Machine Unlearning Techniques for Image and Text Classification Models | arXiv | 2024 | Link |
| A More Practical Approach to Machine Unlearning | arXiv | 2024 | Link |
| A Review on Machine Unlearning | arXiv | 2024 | Link |
| A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions | arXiv | 2024 | Link |
| A Unified Framework for Continual Learning and Unlearning | arXiv | 2024 | Link |
| A hybrid framework for effective and efficient machine unlearning | arXiv | 2024 | Link |
| AND: Audio Network Dissection for Interpreting Deep Acoustic Models | arXiv | 2024 | Link |
| Accurate Forgetting for All-in-One Image Restoration Model | arXiv | 2024 | Link |
| Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models | arXiv | 2024 | Link |
| An Adversarial Perspective on Machine Unlearning for AI Safety | arXiv | 2024 | Link |
| An Information Theoretic Approach to Machine Unlearning | arXiv | 2024 | Link |
| Attack and Reset for Unlearning: Exploiting Adversarial Noise toward Machine Unlearning through Parameter Re-initialization | arXiv | 2024 | Link |
| Attribute-to-Delete: Machine Unlearning via Datamodel Matching | arXiv | 2024 | Link |
| Automatic Jailbreaking of the Text-to-Image Generative AI Systems | arXiv | 2024 | Link |
| Boosting Alignment for Post-Unlearning Text-to-Image Generative Models | arXiv | 2024 | Link |
| CLEAR: Character Unlearning in Textual and Visual Modalities | arXiv | 2024 | Link |
| CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP | arXiv | 2024 | Link |
| CPR: Retrieval Augmented Generation for Copyright Protection | arXiv | 2024 | Link |
| CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence | arXiv | 2024 | Link |
| CaMU: Disentangling Causal Effects in Deep Model Unlearning | arXiv | 2024 | Link |
| Certified Machine Unlearning via Noisy Stochastic Gradient Descent | arXiv | 2024 | Link |
| Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning | arXiv | 2024 | Link |
| Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning | arXiv | 2024 | Link |
| CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept | arXiv | 2024 | Link |
| Composable Interventions for Language Models | arXiv | 2024 | Link |
| Contrastive Unlearning: A Contrastive Approach to Machine Unlearning | arXiv | 2024 | Link |
| Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$-Constrained Optimization | arXiv | 2024 | Link |
| Corrective Machine Unlearning | arXiv | 2024 | Link |
| Cross-Lingual Unlearning of Selective Knowledge in Multilingual Language Models | arXiv | 2024 | Link |
| Data Selection for Transfer Unlearning | arXiv | 2024 | Link |
| Debiasing Machine Unlearning with Counterfactual Examples | arXiv | 2024 | Link |
| Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning | arXiv | 2024 | Link |
| Decoupling the Class Label and the Target Concept in Machine Unlearning | arXiv | 2024 | Link |
| Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models | arXiv | 2024 | Link |
| Digital Forgetting in Large Language Models: A Survey of Unlearning Methods | arXiv | 2024 | Link |
| Dissecting Language Models: Machine Unlearning via Selective Pruning | arXiv | 2024 | Link |
| Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting | arXiv | 2024 | Link |
| Don't Forget Too Much: Towards Machine Unlearning on Feature Level | arXiv | 2024 | Link |
| DynFrs: An Efficient Framework for Machine Unlearning in Random Forest | arXiv | 2024 | Link |
| Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices | arXiv | 2024 | Link |
| Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats | arXiv | 2024 | Link |
| Efficient Knowledge Deletion from Trained Models through Layer-wise Partial Machine Unlearning | arXiv | 2024 | Link |
| Eight Methods to Evaluate Robust Unlearning in LLMs | arXiv | 2024 | Link |
| Enhancing User-Centric Privacy Protection: An Interactive Framework through Diffusion Models and Machine Unlearning | arXiv | 2024 | Link |
| Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction | arXiv | 2024 | Link |
| Erasing Undesirable Influence in Diffusion Models | arXiv | 2024 | Link |
| Evaluating Deep Unlearning in Large Language Models | arXiv | 2024 | Link |
| Example-based Explanations for Random Forests using Machine Unlearning | arXiv | 2024 | Link |
| Exploring Fairness in Educational Data Mining in the Context of the Right to be Forgotten | arXiv | 2024 | Link |
| Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification | arXiv | 2024 | Link |
| From Machine Learning to Machine Unlearning: Complying with GDPR's Right to be Forgotten while Maintaining Business Value of Predictive Models | arXiv | 2024 | Link |
| GENIU: A Restricted Data Access Unlearning for Imbalanced Data | arXiv | 2024 | Link |
| Generative Unlearning for Any Identity | arXiv | 2024 | Link |
| GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning | arXiv | 2024 | Link |
| Hessian-Free Online Certified Unlearning | arXiv | 2024 | Link |
| Improved Localized Machine Unlearning Through the Lens of Memorization | arXiv | 2024 | Link |
| Instance-Level Difficulty: A Missing Perspective in Machine Unlearning | arXiv | 2024 | Link |
| Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images | arXiv | 2024 | Link |
| LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet | arXiv | 2024 | Link |
| LMEraser: Large Model Unlearning through Adaptive Prompt Tuning | arXiv | 2024 | Link |
| Label Smoothing Improves Machine Unlearning | arXiv | 2024 | Link |
| Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models | arXiv | 2024 | Link |
| Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning | arXiv | 2024 | Link |
| Learn to Unlearn: Meta-Learning-Based Knowledge Graph Embedding Unlearning | arXiv | 2024 | Link |
| Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models | arXiv | 2024 | Link |
| Learning to Forget using Hypernetworks | arXiv | 2024 | Link |
| Learning to Refuse: Towards Mitigating Privacy Risks in LLMs | arXiv | 2024 | Link |
| Learning to Unlearn for Robust Machine Unlearning | arXiv | 2024 | Link |
| LoRA Unlearns More and Retains More (Student Abstract) | arXiv | 2024 | Link |
| Loss-Free Machine Unlearning | arXiv | 2024 | Link |
| MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning | arXiv | 2024 | Link |
| MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation | arXiv | 2024 | Link |
| MUNBa: Machine Unlearning via Nash Bargaining | arXiv | 2024 | Link |
| MUSO: Achieving Exact Machine Unlearning in Over-Parameterized Regimes | arXiv | 2024 | Link |
| Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research | arXiv | 2024 | Link |
| Machine Unlearning Fails to Remove Data Poisoning Attacks | arXiv | 2024 | Link |
| Machine Unlearning for Document Classification | arXiv | 2024 | Link |
| Machine Unlearning for Image-to-Image Generative Models | arXiv | 2024 | Link |
| Machine Unlearning for Medical Imaging | arXiv | 2024 | Link |
| Machine Unlearning for Recommendation Systems: An Insight | arXiv | 2024 | Link |
| Machine Unlearning for Speaker-Agnostic Detection of Gender-Based Violence Condition in Speech | arXiv | 2024 | Link |
| Machine Unlearning for Traditional Models and Large Language Models: A Short Survey | arXiv | 2024 | Link |
| Machine Unlearning in Contrastive Learning | arXiv | 2024 | Link |
| Machine Unlearning in Forgettability Sequence | arXiv | 2024 | Link |
| Machine Unlearning in Generative AI: A Survey | arXiv | 2024 | Link |
| Machine Unlearning in Large Language Models | arXiv | 2024 | Link |
| Machine Unlearning of Pre-trained Large Language Models | arXiv | 2024 | Link |
| Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA | arXiv | 2024 | Link |
| Machine Unlearning via Null Space Calibration | arXiv | 2024 | Link |
| Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects | arXiv | 2024 | Link |
| Machine unlearning through fine-grained model parameters perturbation | arXiv | 2024 | Link |
| Mitigating Backdoor Attacks using Activation-Guided Model Editing | arXiv | 2024 | Link |
| Mitigating Memorization In Language Models | arXiv | 2024 | Link |
| Mitigating Social Biases in Language Models through Unlearning | arXiv | 2024 | Link |
| Model Integrity when Unlearning with T2I Diffusion Models | arXiv | 2024 | Link |
| Moderating the Generalization of Score-based Generative Model | arXiv | 2024 | Link |
| NegMerge: Sign-Consensual Weight Merging for Machine Unlearning | arXiv | 2024 | Link |
| Neural Corrective Machine Unranking | arXiv | 2024 | Link |
| Neural Machine Unranking | arXiv | 2024 | Link |
| Noise is All You Need: Private Second-Order Convergence of Noisy SGD | arXiv | 2024 | Link |
| On Newton's Method to Unlearn Neural Networks | arXiv | 2024 | Link |
| On the Limitations and Prospects of Machine Unlearning for Generative AI | arXiv | 2024 | Link |
| Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport | arXiv | 2024 | Link |
| Partially Blinded Unlearning: Class Unlearning for Deep Networks a Bayesian Perspective | arXiv | 2024 | Link |
| Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions | arXiv | 2024 | Link |
| Promoting User Data Autonomy During the Dissolution of a Monopolistic Firm | arXiv | 2024 | Link |
| Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models | arXiv | 2024 | Link |
| Provable unlearning in topic modeling and downstream tasks | arXiv | 2024 | Link |
| RESTOR: Knowledge Recovery in Machine Unlearning | arXiv | 2024 | Link |
| RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models | arXiv | 2024 | Link |
| Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable | arXiv | 2024 | Link |
| Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning | arXiv | 2024 | Link |
| Remaining-data-free Machine Unlearning by Suppressing Sample Contribution | arXiv | 2024 | Link |
| Remembering Everything Makes You Vulnerable: A Limelight on Machine Unlearning for Personalized Healthcare Sector | arXiv | 2024 | Link |
| Revisiting Machine Unlearning with Dimensional Alignment | arXiv | 2024 | Link |
| Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions | arXiv | 2024 | Link |
| SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness | arXiv | 2024 | Link |
| Scalability of memorization-based machine unlearning | arXiv | 2024 | Link |
| Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks | arXiv | 2024 | Link |
| Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models | arXiv | 2024 | Link |
| Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models | arXiv | 2024 | Link |
| Separable Multi-Concept Erasure from Diffusion Models | arXiv | 2024 | Link |
| Soft Prompting for Unlearning in Large Language Models | arXiv | 2024 | Link |
| Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs | arXiv | 2024 | Link |
| Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphs | arXiv | 2024 | Link |
| Targeted Unlearning with Single Layer Unlearning Gradient | arXiv | 2024 | Link |
| Textual Unlearning Gives a False Sense of Unlearning | arXiv | 2024 | Link |
| The Frontier of Data Erasure: Machine Unlearning for Large Language Models | arXiv | 2024 | Link |
| The Utility and Complexity of in- and out-of-Distribution Machine Unlearning | arXiv | 2024 | Link |
| Toward Efficient Data-Free Unlearning | arXiv | 2024 | Link |
| Towards Aligned Data Removal via Twin Machine Unlearning | arXiv | 2024 | Link |
| Towards Certified Unlearning for Deep Neural Networks | arXiv | 2024 | Link |
| Towards Effective and General Graph Unlearning via Mutual Evolution | arXiv | 2024 | Link |
| Towards Efficient Target-Level Machine Unlearning Based on Essential Graph | arXiv | 2024 | Link |
| Towards Independence Criterion in Machine Unlearning of Features and Labels | arXiv | 2024 | Link |
| Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Approximate Unlearning Completeness | arXiv | 2024 | Link |
| Towards Natural Machine Unlearning | arXiv | 2024 | Link |
| Towards Robust Evaluation of Unlearning in LLMs via Data Transformations | arXiv | 2024 | Link |
| Towards Safer Large Language Models through Machine Unlearning | arXiv | 2024 | Link |
| Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning | arXiv | 2024 | Link |
| TruVRF: Towards Triple-Granularity Verification on Machine Unlearning | arXiv | 2024 | Link |
| Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspective | arXiv | 2024 | Link |
| Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement | arXiv | 2024 | Link |
| Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy | arXiv | 2024 | Link |
| UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models | arXiv | 2024 | Link |
| Unlearning Concepts in Diffusion Model via Concept Domain Correction and Concept Preserving Gradient | arXiv | 2024 | Link |
| Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases | arXiv | 2024 | Link |
| Unlearning Personal Data from a Single Image | arXiv | 2024 | Link |
| Unlearning Trojans in Large Language Models: A Comparison Between Natural Language and Source Code | arXiv | 2024 | Link |
| Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate | arXiv | 2024 | Link |
| Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method | arXiv | 2024 | Link |
| Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning | arXiv | 2024 | Link |
| Verification of Machine Unlearning is Fragile | arXiv | 2024 | Link |
| Verifying Machine Unlearning with Explainable AI | arXiv | 2024 | Link |
| ViT-MUL: A Baseline Study on Recent Machine Unlearning Methods Applied to Vision Transformers | arXiv | 2024 | Link |
| What makes unlearning hard and what to do about it | arXiv | 2024 | Link |
| When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge? | arXiv | 2024 | Link |
| Zero-Shot Class Unlearning in CLIP with Synthetic Samples | arXiv | 2024 | Link |
| Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation | arXiv | 2024 | Link |
| eCIL-MU: Embedding based Class Incremental Learning and Machine Unlearning | arXiv | 2024 | Link |
2023
| Title | Venue | Year | Link |
|---|---|---|---|
| A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services | arXiv | 2023 | Link |
| Boundary Unlearning | arXiv | 2023 | Link |
| Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning | arXiv | 2023 | Link |
| Certified Minimax Unlearning with Generalization Rates and Deletion Capacity | arXiv | 2023 | Link |
| DUCK: Distance-based Unlearning via Centroid Kinematics | arXiv | 2023 | Link |
| DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal | arXiv | 2023 | Link |
| Detecting Pretraining Data from Large Language Models | arXiv | 2023 | Link |
| ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach | arXiv | 2023 | Link |
| Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System | arXiv | 2023 | Link |
| Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy | arXiv | 2023 | Link |
| FAST: Feature Aware Similarity Thresholding for Weak Unlearning in Black-Box Generative Models | arXiv | 2023 | Link |
| Fair Machine Unlearning: Data Removal while Mitigating Disparities | arXiv | 2023 | Link |
| Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening | arXiv | 2023 | Link |
| Fast Model Debias with Machine Unlearning | arXiv | 2023 | Link |
| Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models | arXiv | 2023 | Link |
| From Adaptive Query Release to Machine Unlearning | arXiv | 2023 | Link |
| GIF: A General Graph Unlearning Strategy via Influence Function | arXiv | 2023 | Link |
| Generative Adversarial Networks Unlearning | arXiv | 2023 | Link |
| Gradient Surgery for One-shot Unlearning on Generative Model | arXiv | 2023 | Link |
| Heterogeneous Decentralized Machine Unlearning with Seed Model Distillation | arXiv | 2023 | Link |
| In-Context Unlearning: Language Models as Few Shot Unlearners | arXiv | 2023 | Link |
| Inductive Graph Unlearning | arXiv | 2023 | Link |
| KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment | arXiv | 2023 | Link |
| Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges | arXiv | 2023 | Link |
| Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation | arXiv | 2023 | Link |
| Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection | arXiv | 2023 | Link |
| Learn to Unlearn: A Survey on Machine Unlearning | arXiv | 2023 | Link |
| Machine Unlearning Methodology base on Stochastic Teacher Network | arXiv | 2023 | Link |
| Machine Unlearning for Causal Inference | arXiv | 2023 | Link |
| Machine Unlearning in Learned Databases: An Experimental Analysis | arXiv | 2023 | Link |
| Machine Unlearning: A Survey | arXiv | 2023 | Link |
| Machine Unlearning: Solutions and Challenges | arXiv | 2023 | Link |
| Machine Unlearning: its nature, scope, and importance for a "delete culture" | arXiv | 2023 | Link |
| Model Sparsity Can Simplify Machine Unlearning | arXiv | 2023 | Link |
| Multi-Class Unlearning for Image Classification via Weight Filtering | arXiv | 2023 | Link |
| MultiDelete for Multimodal Machine Unlearning | arXiv | 2023 | Link |
| Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations | arXiv | 2023 | Link |
| One-Shot Machine Unlearning with Mnemonic Code | arXiv | 2023 | Link |
| Open Knowledge Base Canonicalization with Multi-task Unlearning | arXiv | 2023 | Link |
| Privacy and Copyright Protection in Generative AI: A Lifecycle Perspective | arXiv | 2023 | Link |
| Random Relabeling for Efficient Machine Unlearning | arXiv | 2023 | Link |
| Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions | arXiv | 2023 | Link |
| SAFE: Machine Unlearning With Shard Graphs | arXiv | 2023 | Link |
| SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation | arXiv | 2023 | Link |
| Split Unlearning | arXiv | 2023 | Link |
| Tangent Transformers for Composition, Privacy and Removal | arXiv | 2023 | Link |
| Task-Aware Machine Unlearning and Its Application in Load Forecasting | arXiv | 2023 | Link |
| Tight Bounds for Machine Unlearning via Differential Privacy | arXiv | 2023 | Link |
| To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods | arXiv | 2023 | Link |
| Towards Machine Unlearning Benchmarks: Forgetting the Personal Identities in Facial Recognition Systems | arXiv | 2023 | Link |
| Unfolded Self-Reconstruction LSH: Towards Machine Unlearning in Approximate Nearest Neighbour Search | arXiv | 2023 | Link |
| Unlearning with Fisher Masking | arXiv | 2023 | Link |
2022
| Title | Venue | Year | Link |
|---|---|---|---|
| A Survey of Machine Unlearning | arXiv | 2022 | Link |
| An Introduction to Machine Unlearning | arXiv | 2022 | Link |
| Backdoor Defense with Machine Unlearning | arXiv | 2022 | Link |
| Bounding Membership Inference | arXiv | 2022 | Link |
| Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher | arXiv | 2022 | Link |
| Certified Graph Unlearning | arXiv | 2022 | Link |
| Challenges and Pitfalls of Bayesian Unlearning | arXiv | 2022 | Link |
| Control, Confidentiality, and the Right to be Forgotten | arXiv | 2022 | Link |
| Deep Regression Unlearning | arXiv | 2022 | Link |
| Deep Unlearning via Randomized Conditionally Independent Hessians | arXiv | 2022 | Link |
| Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning | arXiv | 2022 | Link |
| Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations | arXiv | 2022 | Link |
| Evaluating Machine Unlearning via Epistemic Uncertainty | arXiv | 2022 | Link |
| Forget Unlearning: Towards True Data-Deletion in Machine Learning | arXiv | 2022 | Link |
| Forgetting Fast in Recommender Systems | arXiv | 2022 | Link |
| Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks | arXiv | 2022 | Link |
| Knowledge Removal in Sampling-based Bayesian Inference | arXiv | 2022 | Link |
| LegoNet: A Fast and Exact Unlearning Architecture | arXiv | 2022 | Link |
| Machine Unlearning Method Based On Projection Residual | arXiv | 2022 | Link |
| Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation | arXiv | 2022 | Link |
| Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten | arXiv | 2022 | Link |
| Membership Inference via Backdooring | arXiv | 2022 | Link |
| PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning | arXiv | 2022 | Link |
| Privacy Adhering Machine Un-learning in NLP | arXiv | 2022 | Link |
| Proof of Unlearning: Definitions and Instantiation | arXiv | 2022 | Link |
| Recommendation Unlearning | arXiv | 2022 | Link |
| Towards Adversarial Evaluations for Inexact Machine Unlearning | arXiv | 2022 | Link |
| Unlearning Graph Classifiers with Limited Data Resources | arXiv | 2022 | Link |
| Verifiable and Provably Secure Machine Unlearning | arXiv | 2022 | Link |
2021
| Title | Venue | Year | Link |
|---|---|---|---|
| A unified PAC-Bayesian framework for machine unlearning via information risk minimization | arXiv | 2021 | Link |
| Adaptive Machine Unlearning | arXiv | 2021 | Link |
| An Investigation on Learning, Polluting, and Unlearning the Spam Emails for Lifelong Learning | arXiv | 2021 | Link |
| Certifiable Machine Unlearning for Linear Models | arXiv | 2021 | Link |
| DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks | arXiv | 2021 | Link |
| Fast Yet Effective Machine Unlearning | arXiv | 2021 | Link |
| Graph Unlearning | arXiv | 2021 | Link |
| Hard to Forget: Poisoning Attacks on Certified Machine Unlearning | arXiv | 2021 | Link |
| Lightweight machine unlearning in neural network | arXiv | 2021 | Link |
| Machine Unlearning of Features and Labels | arXiv | 2021 | Link |
| Machine Unlearning via Algorithmic Stability | arXiv | 2021 | Link |
| On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning | arXiv | 2021 | Link |
| Remember What You Want to Forget: Algorithms for Machine Unlearning | arXiv | 2021 | Link |
| Unrolling SGD: Understanding Factors Influencing Machine Unlearning | arXiv | 2021 | Link |
2020
| Title | Venue | Year | Link |
|---|---|---|---|
| Coded Machine Unlearning | arXiv | 2020 | Link |
| Descent-to-Delete: Gradient-Based Methods for Machine Unlearning | arXiv | 2020 | Link |
| Learn to Forget: Machine Unlearning via Neuron Masking | arXiv | 2020 | Link |
| Machine Unlearning for Random Forests | arXiv | 2020 | Link |
| Machine Unlearning: Linear Filtration for Logit-based Classifiers | arXiv | 2020 | Link |
| Towards Probabilistic Verification of Machine Unlearning | arXiv | 2020 | Link |
2019
| Title | Venue | Year | Link |
|---|---|---|---|
| Machine Unlearning | arXiv | 2019 | Link |