AI Safety

SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models ICML 2025 SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities ACL 2025 SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models EMNLP 2025 Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets ICML 2025 Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection ACL 2025 Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks ICCV 2025 SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models AAAI 2025 Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs ACL 2025 Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Models NAACL 2025 SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Intervention EMNLP 2025 SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025 SafeMimic: Towards Safe and Autonomous Human-to-Robot Imitation for Mobile Manipulation RSS 2025 SAFENUDGE: Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs EMNLP 2025 Safe Planner: Empowering Safety Awareness in Large Pre-Trained Models for Robot Task Planning AAAI 2025 SafeQuant: LLM Safety Analysis via Quantized Gradient Inspection NAACL 2025 SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model ACL 2025 Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts ACL 2025 SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers ICCV 2025 SafeScientist: Enhancing AI Scientist Safety for Risk-Aware Scientific Discovery EMNLP 2025 SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signals EMNLP 2025 SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs EMNLP 2025 Safety Alignment Can Be Not Superficial With Explicit Safety Signals ICML 2025 Safety Alignment Should be Made More Than Just a Few Tokens Deep ICLR 2025 Safety Alignment via Constrained Knowledge Unlearning ACL 2025 SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior ICML 2025