Safety

Investigating the Security Threat Arising from “Yes-No” Implicit Bias in Large Language Models AAAI 2025 IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents EMNLP 2025 Jailbreaking? One Step Is Enough! ACL 2025 Jailbreak Large Vision-Language Models Through Multi-Modal Linkage ACL 2025 Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers EMNLP 2025 Learning for Layered Safety-Critical Control with Predictive Control Barrier Functions L4DC 2025 Learning Geometrically-Informed Lyapunov Functions with Deep Diffeomorphic RBF Networks AISTATS 2025 Learn With Imagination: Safe Set Guided State-wise Constrained Policy Optimization L4DC 2025 LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint ACL 2025 LEGEND: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets AAAI 2025 Leveraging Constraint Violation Signals for Action Constrained Reinforcement Learning AAAI 2025 LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges ACL 2025 LongSafety: Evaluating Long-Context Safety of Large Language Models ACL 2025 Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling ACL 2025 Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key CVPR 2025 MMJ-Bench: A Comprehensive Study on Jailbreak Attacks and Defenses for Vision Language Models AAAI 2025 MPO: Multilingual Safety Alignment via Reward Gap Optimization ACL 2025 MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety EMNLP 2025 Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems AAAI 2025 Multi-Constraint Safe Reinforcement Learning via Closed-form Solution for Log-Sum-Exp Approximation of Control Barrier Functions L4DC 2025 Multimodal Pragmatic Jailbreak on Text-to-image Models ACL 2025 MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models EMNLP 2025 Neural Network-assisted Interval Reachability for Systems with Control Barrier Function-Based Safe Controllers L4DC 2025 NLP for Counterspeech against Hate and Misinformation (CSHAM) ACL 2025 NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning AAAI 2025