Safety

Nullspace Disentanglement for Red Teaming Language Models EMNLP 2025 Offline Safe Reinforcement Learning Using Trajectory Classification AAAI 2025 PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization EMNLP 2025 PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free ACL 2025 PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference ACL 2025 PL-Guard: Benchmarking Language Model Safety for Polish ACL 2025 Predictive Monitoring of Black-Box Dynamical Systems L4DC 2025 Preventing Rogue Agents Improves Multi-Agent Collaboration ACL 2025 Probabilistic Shielding for Safe Reinforcement Learning AAAI 2025 PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks AAAI 2025 QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety ACL 2025 Quantitative Predictive Monitoring and Control for Safe Human-Machine Interaction AAAI 2025 QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language ACL 2025 Realizable Continuous-Space Shields for Safe Reinforcement Learning L4DC 2025 Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking EMNLP 2025 Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training ACL 2025 Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Context EMNLP 2025 Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective AAAI 2025 Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction ACL 2025 Robust Transfer of Safety-Constrained Reinforcement Learning Agents ICLR 2025 Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level ACL 2025 Safe Cooperative Multi-Agent Reinforcement Learning with Function Approximation L4DC 2025 Safe Decision Transformer with Learning-based Constraints L4DC 2025 Safe Exploration in Reinforcement Learning: Training Backup Control Barrier Functions with Zero Training-Time Safety Violations L4DC 2025 SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models AAAI 2025