AI Safety

A Reinforcement Learning Framework for Robust and Secure LLM Watermarking EACL 2026 Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers EACL 2026 ARREST: Adversarial Resilient Regulation Enhancing Safety and Truth in Large Language Models EACL 2026 Artificial Immune System of Secure Face Recognition Against Adversarial Attacks (Abstract Reprint) AAAI 2026 AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin AAAI 2026 A Simple and Efficient Learning-Style Prompting for LLM Jailbreaking EACL 2026 Assertion-Conditioned Compliance: A Provenance-Aware Vulnerability in Multi-Turn Tool-Calling Agents EACL 2026 ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs ACL 2026 Attacker’s Noise Can Manipulate Your Audio-based LLM in the Real World EACL 2026 Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS AAAI 2026 Attribution-Guided Multi-Object Hallucination and Bias Detection in Vision-Language Models EACL 2026 Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models ACL 2026 AuditAgent: LLM Agent for Risks Auditing in Recommender Systems AAAI 2026 AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models AAAI 2026 Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs AAAI 2026 AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models ACL 2026 Backdooring Rationalization AAAI 2026 BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers? ACL 2026 BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models AAAI 2026 BAFLE-DCT: Bypassing Adversarial Filters via Frequency-Selective Embedding in the DCT Domain WACV 2026 BarrierBench: Evaluating Large Language Models for Safety Verification in Dynamical Systems L4DC 2026 Being Kind Isn’t Always Being Safe: Diagnosing Affective Hallucination in LLMs EACL 2026 Benchmarking and Enhancing Rule Knowledge-Driven Reasoning of Large Language Models AAAI 2026 Benchmarking Trustworthiness in Multimodal LLMs for Video Understanding AAAI 2026 Benchmarking Visual LLMs Resilience to Unanswerable Questions on Visually Rich Documents AAAI 2026