Safety

Decoding-Unlearning: Fact Forgetting via Entropy-Guided Inference ACL 2026 Deep QP Safety Filter: Model-free Learning for Reachability-based Safety Filter L4DC 2026 Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety ACL 2026 Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation Monitoring ACL 2026 Detoxification for LLM: From Dataset Itself ACL 2026 DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs ACL 2026 Don’t Click That: Teaching Web Agents to Resist Deceptive Interfaces ACL 2026 DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping ACL 2026 Dynamic Token Reweighting for Robust Vision-Language Models CVPR 2026 Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance ACL 2026 EthicMind: A Risk-Aware Framework for Ethical-Emotional Alignment in Multi-Turn Dialogue ACL 2026 Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks ACL 2026 Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory CVPR 2026 Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection ACL 2026 FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models ACL 2026 FinHarmBench: Financial Jailbreak Benchmark and Unsupervised Safety Fine-Tuning via Refusal Steering Distillation ACL 2026 FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation ACL 2026 Forget What Matters, Keep the Rest: Selective Unlearning of Informative Tokens ACL 2026 Foundations of Safe Online Reinforcement Learning in the Linear Quadratic Regulator: √T-Regret L4DC 2026 GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models ACL 2026 Gradient-Guided Reward Optimization for Inference-time Alignment UAI 2026 Hallucination Detection in LLMs with Topological Divergence on Attention Graphs ACL 2026 HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment ACL 2026 Hidden Dangers of Compositional Generation: Diagnosing Semantic Safety Failures in Text-to-Image Models CVPR 2026 HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router ACL 2026