AI Safety

Safety in Large Reasoning Models: A Survey EMNLP 2025 Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety ACL 2025 Safety Layers in Aligned Large Language Models: The Key to LLM Security ICLR 2025 Safety of Embodied Navigation: A Survey IJCAI 2025 Safety-Polarized and Prioritized Reinforcement Learning ICML 2025 SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety AAAI 2025 SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs NAACL 2025 Safety Reasoning with Guidelines ICML 2025 Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models EMNLP 2025 SAGE: A Generic Framework for LLM Safety Evaluation EMNLP 2025 Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking ICLR 2025 SAM Encoder Breach by Adversarial Simplicial Complex Triggers Downstream Model Failures ICCV 2025 Sampling-based Pseudo-Likelihood for Membership Inference Attacks ACL 2025 SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage ACL 2025 Scalable Surrogate Verification of Image-Based Neural Network Control Systems Using Composition and Unrolling AAAI 2025 Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens ICLR 2025 Scaling Trends for Data Poisoning in LLMs AAAI 2025 SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering AAAI 2025 SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments CVPR 2025 SConU: Selective Conformal Uncertainty in Large Language Models ACL 2025 SDBF: Steep-Decision-Boundary Fingerprinting for Hard-Label Tampering Detection of DNN Models CVPR 2025 SDD: Self-Degraded Defense against Malicious Fine-tuning ACL 2025 SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models EMNLP 2025 SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming ICML 2025 SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings ACL 2025