AI Safety

Exploiting Instruction-Following Retrievers for Malicious Information Retrieval ACL 2025 Exploiting Prompt-induced Confidence for Black-Box Attacks on LLMs EMNLP 2025 Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models COLING 2025 Exploiting the Shadows: Unveiling Privacy Leaks through Lower-Ranked Tokens in Large Language Models ACL 2025 Explore Theory of Mind: program-guided adversarial data generation for theory of mind reasoning ICLR 2025 Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards ICML 2025 Exploring Backdoor Vulnerabilities of Chat Models COLING 2025 Exploring Intrinsic Alignments Within Text Corpus AAAI 2025 Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion ACL 2025 Exploring LLMs’ Ability to Spontaneously and Conditionally Modify Moral Expressions through Text Manipulation ACL 2025 Exploring Straightforward Methods for Automatic Conversational Red-Teaming NAACL 2025 Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics ICCV 2025 Exploring the Impact of Instruction-Tuning on LLM’s Susceptibility to Misinformation ACL 2025 Exploring the Impact of Personality Traits on LLM Bias and Toxicity EMNLP 2025 Exploring the Role of Mental Health Conversational Agents in Training Medical Students and Professionals: A Systematic Literature Review ACL 2025 Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation EMNLP 2025 Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models CVPR 2025 Extended Abstract: Probing-Guided Parameter-Efficient Fine-Tuning for Balancing Linguistic Adaptation and Safety in LLM-based Social Influence Systems ACL 2025 Extracting and Understanding the Superficial Knowledge in Alignment NAACL 2025 Extreme Value Policy Optimization for Safe Reinforcement Learning ICML 2025 Failures to Find Transferable Image Jailbreaks Between Vision-Language Models ICLR 2025 Fairness Shields: Safeguarding against Biased Decision Makers AAAI 2025 Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations ACL 2025 FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge EMNLP 2025 Fantastic Copyrighted Beasts and How (Not) to Generate Them ICLR 2025