Reading lists / Prompt Injection Attack
Prompt Injection Attack
Table of Contents
NeurIPS
ICML
ICLR
KDD
SP
CCS
USENIX Security Symposium
ACL
NAACL-HLT
EMNLP
ICSE
ICDM
ACM Multimedia
IEEE Trans. Image Process.
IEEE Trans. Inf. Forensics Secur.
arXiv
NeurIPS
Expand NeurIPS
2024
| Title |
Venue |
Year |
Link |
| AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents. |
NeurIPS |
2024 |
Link |
ICML
Expand ICML
2025
| Title |
Venue |
Year |
Link |
| MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents. |
ICML |
2025 |
Link |
ICLR
Expand ICLR
2024
| Title |
Venue |
Year |
Link |
| Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game. |
ICLR |
2024 |
Link |
KDD
Expand KDD
2025
| Title |
Venue |
Year |
Link |
| Benchmarking and Defending against Indirect Prompt Injection Attacks on Large Language Models. |
KDD |
2025 |
Link |
| Generalizable Graph Prompt Learning Framework with Model-level Prompt Injection and Two-Stage Prompt Tuning. |
KDD |
2025 |
Link |
SP
Expand SP
2025
| Title |
Venue |
Year |
Link |
| DataSentinel: A Game-Theoretic Detection of Prompt Injection Attacks. |
SP |
2025 |
Link |
| Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-Based Prompt Injection Attacks via the Fine-Tuning Interface. |
SP |
2025 |
Link |
2024
| Title |
Venue |
Year |
Link |
| PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification. |
SP |
2024 |
Link |
CCS
Expand CCS
2025
| Title |
Venue |
Year |
Link |
| SecAlign: Defending Against Prompt Injection with Preference Optimization. |
CCS |
2025 |
Link |
2024
| Title |
Venue |
Year |
Link |
| Optimization-based Prompt Injection Attack to LLM-as-a-Judge. |
CCS |
2024 |
Link |
USENIX Security Symposium
Expand USENIX Security Symposium
2025
| Title |
Venue |
Year |
Link |
| StruQ: Defending Against Prompt Injection with Structured Queries. |
USENIX Security Symposium |
2025 |
Link |
2024
| Title |
Venue |
Year |
Link |
| Formalizing and Benchmarking Prompt Injection Attacks and Defenses. |
USENIX Security Symposium |
2024 |
Link |
ACL
Expand ACL
2025
| Title |
Venue |
Year |
Link |
| Can Indirect Prompt Injection Attacks Be Detected and Removed? |
ACL |
2025 |
Link |
| Defense Against Prompt Injection Attack by Leveraging Attack Techniques. |
ACL |
2025 |
Link |
| PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free. |
ACL |
2025 |
Link |
| The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents. |
ACL |
2025 |
Link |
2024
| Title |
Venue |
Year |
Link |
| InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents. |
ACL |
2024 |
Link |
NAACL-HLT
Expand NAACL-HLT
2024
| Title |
Venue |
Year |
Link |
| Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection. |
NAACL-HLT |
2024 |
Link |
EMNLP
Expand EMNLP
2025
| Title |
Venue |
Year |
Link |
| AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents. |
EMNLP |
2025 |
Link |
| Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods. |
EMNLP |
2025 |
Link |
| Defending against Indirect Prompt Injection by Instruction Detection. |
EMNLP |
2025 |
Link |
| IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents. |
EMNLP |
2025 |
Link |
| Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models. |
EMNLP |
2025 |
Link |
| The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration. |
EMNLP |
2025 |
Link |
| TopicAttack: An Indirect Prompt Injection Attack via Topic Transition. |
EMNLP |
2025 |
Link |
| Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling. |
EMNLP |
2025 |
Link |
| WebInject: Prompt Injection Attack to Web Agents. |
EMNLP |
2025 |
Link |
2024
| Title |
Venue |
Year |
Link |
| Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection. |
EMNLP |
2024 |
Link |
ICSE
Expand ICSE
2025
| Title |
Venue |
Year |
Link |
| Prompt-to-SQL Injections in LLM-Integrated Web Applications: Risks and Defenses. |
ICSE |
2025 |
Link |
ICDM
Expand ICDM
2024
| Title |
Venue |
Year |
Link |
| Goal-Guided Generative Prompt Injection Attack on Large Language Models. |
ICDM |
2024 |
Link |
Expand ACM Multimedia
2025
| Title |
Venue |
Year |
Link |
| Manipulating Multimodal Agents via Cross-Modal Prompt Injection. |
ACM Multimedia |
2025 |
Link |
IEEE Trans. Image Process.
Expand IEEE Trans. Image Process.
2026
| Title |
Venue |
Year |
Link |
| CRISP: Contrastive Residual Injection and Semantic Prompting for Continual Video Instance Segmentation. |
IEEE Trans. Image Process. |
2026 |
Link |
IEEE Trans. Inf. Forensics Secur.
Expand IEEE Trans. Inf. Forensics Secur.
2026
| Title |
Venue |
Year |
Link |
| PromptFuzz: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs. |
IEEE Trans. Inf. Forensics Secur. |
2026 |
Link |
arXiv
Expand arXiv
2026
| Title |
Venue |
Year |
Link |
| AgentWatcher: A Rule-based Prompt Injection Monitor |
arXiv |
2026 |
2604.01194 |
| AttackEval: A Systematic Empirical Study of Prompt Injection Attack Effectiveness Against Large Language Models |
arXiv |
2026 |
2604.03598 |
| Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework |
arXiv |
2026 |
2604.03912 |
| ClawSafety: "Safe" LLMs, Unsafe Agents |
arXiv |
2026 |
2604.01438 |
| Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation |
arXiv |
2026 |
2604.05150 |
| Credential Leakage in LLM Agent Skills: A Large-Scale Empirical Study |
arXiv |
2026 |
2604.03070 |
| Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering |
arXiv |
2026 |
2604.05179 |
| LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation |
arXiv |
2026 |
2604.02954 |
| ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems |
arXiv |
2026 |
2604.04426 |
| Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs |
arXiv |
2026 |
2604.03870 |