AI Safety

RST-Guarder: Enhancing Long-Context Robustness for Safeguards via RST Parsing and Probabilistic Inference ACL 2026 SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African Context EACL 2026 SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator ACL 2026 SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering ACL 2026 Safeguarding Language Models via Self-Destruct Trapdoor EACL 2026 SafeLogo: Turning Your Logos into Jailbreak Shields via Micro-Regional Adversarial Training CVPR 2026 SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories AAAI 2026 Safe Multi-Agent Reinforcement Learning via Distributional Safety Critic and Maximum Entropy Optimization AAAI 2026 Safe Multi-agent Reinforcement Learning with Natural Language Constraints AAAI 2026 SafeNLIDB: A Privacy-Preserving Safety Alignment Framework for LLM-based Natural Language Database Interfaces AAAI 2026 Safe RAG by RAG: Untying the Bell That RAG Rang with the RAG Hand AAAI 2026 Safe Reinforcement Learning for Trustworthy AI: Theory, Algorithms, and Applications AAAI 2026 SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents EACL 2026 Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions AAAI 2026 SafetyReminder: Reviving Delayed Safety Awareness of Vision-Language Models to Defend Against Jailbreak Attacks AAAI 2026 Safe-Unsafe Concept Separation Emerges from a Single Direction in Language Models Activation Space EACL 2026 Scalable Synthesis of Formally Verified Neural Value Function for Hamilton-Jacobi Reachability Analysis (Abstract Reprint) AAAI 2026 Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation L4DC 2026 Scaling Up AI Alignment AAAI 2026 SceneJailEval: A Scenario-Adaptive Multi-Dimensional Framework for Jailbreak Evaluation AAAI 2026 Selective Weak-to-Strong Generalization AAAI 2026 SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance Trigger ACL 2026 ShadeEdit: A Utility-Preserving and Defense-Evasive Knowledge Manipulation Attack in Federated LLMs AAAI 2026 Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems AAAI 2026 ShieldRAG: Safeguarding Retrieval-Augmented Generation from Untrusted Knowledge Bases AAAI 2026