prompt injection

Intention Analysis Makes LLMs A Good Jailbreak Defender COLING 2025 Jailbreaking as a Reward Misspecification Problem ICLR 2025 Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers EMNLP 2025 LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges ACL 2025 Look Before You Leap: Universal Emergent Mechanism for Retrieval in Language Models ICLR 2025 PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free ACL 2025 Proxy Barrier: A Hidden Repeater Layer Defense Against System Prompt Leakage and Jailbreaking EMNLP 2025 RedHit: Adaptive Red-Teaming of Large Language Models via Search, Reasoning, and Preference Optimization ACL 2025 Role-Aware Language Models for Secure and Contextualized Access Control in Organizations IJCNLP 2025 Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs ACL 2025 Scaling Trends in Language Model Robustness ICML 2025 SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models AAAI 2025 SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains ACL 2025 SQL Injection Jailbreak: A Structural Disaster of Large Language Models ACL 2025 Stepwise Reasoning Disruption Attack of LLMs ACL 2025 Stronger Universal and Transferable Attacks by Suppressing Refusals NAACL 2025 System Prompt Hijacking via Permutation Triggers in LLM Supply Chains ACL 2025 The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration EMNLP 2025 The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 IJCNLP 2025 The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents ACL 2025 The Threat of PROMPTS in Large Language Models: A System and User Prompt Perspective ACL 2025 The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs ACL 2025 TopicAttack: An Indirect Prompt Injection Attack via Topic Transition EMNLP 2025 Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling EMNLP 2025 TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice NAACL 2025