AI Safety

Beta Distribution Learning for Reliable Roadway Crash Risk Assessment AAAI 2026 Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition WACV 2026 Beyond Blind Following: Evaluating Robustness of LLM Agents under Imperfect Guidance EACL 2026 Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal AAAI 2026 Beyond Names: How Grammatical Gender Markers Bias LLM-based Educational Recommendations EACL 2026 Beyond Prompting: AI Safety Education in the Generative AI Era AAAI 2026 Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation ACL 2026 Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning AAAI 2026 Beyond Verdicts: Evaluating Language Model Moral Competence AAAI 2026 Big AI is Accelerating the Metacrisis: What Can We Do? ACL 2026 BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage EACL 2026 Boosting the Robustness-Accuracy Trade-off of SNNs by Robust Temporal Self-Ensemble AAAI 2026 Bootstrapping LLMs via Preference-Based Policy Optimization AAAI 2026 Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models EACL 2026 Breakable Machine: A K–12 Classroom Game for Transformative AI Literacy Through Spoofing and eXplainable AI (XAI) AAAI 2026 Breaking Multimodal LLM Safety via Video-Driven Prompting CVPR 2026 Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization AAAI 2026 BURNS: Backward Underapproximate Reachability for Neural-Feedback-Loop Systems L4DC 2026 Can Editing LLMs Inject Harm? AAAI 2026 CAPO: A Unified Policy Gradient Approach for Reward and Cost Optimization in Safe Reinforcement Learning (Student Abstract) AAAI 2026 Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction AAAI 2026 Causal, Strategic, and Combined Responsibility Attribution in Situation Calculus Concurrent Game Structures AAAI 2026 Certified but Fooled! Breaking Certified Defenses with Ghost Certificates AAAI 2026 Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models AAAI 2026 Characterizing AI Manipulation Risks in Brazilian YouTube Climate Discourse AAAI 2026