Safety

Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study EMNLP 2025 A Safe Exploration Approach to Constrained Markov Decision Processes AISTATS 2025 Automating Steering for Safe Multimodal Large Language Models EMNLP 2025 Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs ACL 2025 Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification EMNLP 2025 CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging CVPR 2025 Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet ACL 2025 Can’t See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs ACL 2025 Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? AAAI 2025 Certification of Speaker Recognition Models to Additive Perturbations AAAI 2025 Certified Mitigation of Worst-Case LLM Copyright Infringement EMNLP 2025 Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models ACL 2025 Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs ACL 2025 COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems Against Semantic Attacks AAAI 2025 Concept Bottleneck Large Language Models ICLR 2025 Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs EMNLP 2025 Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning AAAI 2025 Constraint-Conditioned Actor-Critic for Offline Safe Reinforcement Learning ICLR 2025 Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning EMNLP 2025 Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models ACL 2025 Defense Against Prompt Injection Attack by Leveraging Attack Techniques ACL 2025 Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks ACL 2025 Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization CVPR 2025 Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control ICLR 2025 Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models? CVPR 2025