Safety

Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning ICLR 2025 Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization ACL 2025 English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge EMNLP 2025 Enhancing Robustness in Incremental Learning with Adversarial Training AAAI 2025 EntropyMark: Towards More Harmless Backdoor Watermark via Entropy-based Constraint for Open-source Dataset Copyright Protection CVPR 2025 Erasing Undesirable Influence in Diffusion Models CVPR 2025 Error Detection in Medical Note through Multi Agent Debate ACL 2025 Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study EMNLP 2025 Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation ACL 2025 Exploring the Impact of Instruction-Tuning on LLM’s Susceptibility to Misinformation ACL 2025 Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation EMNLP 2025 FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts AAAI 2025 Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency ACL 2025 FOSP: Fine-tuning Offline Safe Policy through World Models ICLR 2025 Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications ACL 2025 Hallucination Detection in LLMs Using Spectral Features of Attention Maps EMNLP 2025 HalluDetect: Detecting, Mitigating, and Benchmarking Hallucinations in Conversational Systems in the Legal Domain EMNLP 2025 HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents ICLR 2025 HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States ACL 2025 How to Fine-Tune Safely on a Budget: Model Adaptation Using Minimal Resources EMNLP 2025 Hyperbolic Safety-Aware Vision-Language Models CVPR 2025 I2VGuard: Safeguarding Images against Misuse in Diffusion-based Image-to-Video Models CVPR 2025 Improve Safety Training of Large Language Models with Safety-Critical Singular Vectors Localization ACL 2025 Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety EMNLP 2025 Investigating How Pre-training Data Leakage Affects Models’ Reproduction and Detection Capabilities EMNLP 2025