AI Safety

From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data Synthesis AAAI 2026 From Narrow Unlearning to Emergent Misalignment in LLMs ACL 2026 From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge AAAI 2026 From TDMA to CDMA: A Multi-bit Watermark for Diffusion Language Models ACL 2026 GenBreak: Red Teaming Text-to-Image Generation Using Large Language Models CVPR 2026 Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models ACL 2026 GenErase: Generalizable and Semantically-Aware Concept Erasure in Diffusion Models CVPR 2026 Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy ACL 2026 Good Gradients Poison Your Model: Evading Defenses in Federated Learning via Boundary-adaptive Perturbation AAAI 2026 GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models ACL 2026 GuardTrace-VL: Detecting Unsafe Multimodel Reasoning via Iterative Safety Supervision CVPR 2026 Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models AAAI 2026 Hallucination as a Computational Boundary: A Hierarchy of Inevitability and the Oracle Escape AAAI 2026 HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token EACL 2026 HAMLET4Fairness: Enhancing Fairness in AI Pipelines Through Human-Centered AutoML and Argumentation AAAI 2026 HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human–LLM Collaborative Writing ACL 2026 Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned MLLMs CVPR 2026 Hashed Watermark as a Filter: A Unified Defense Against Forging and Overwriting Attacks in Neural Network Watermarking AAAI 2026 Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment Through Latent Acoustic Pattern Triggers AAAI 2026 Hierarchical End-to-End Taylor Bounds for Complete Neural Network Verification L4DC 2026 High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers AAAI 2026 Higher-Order Responsibility AAAI 2026 HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors AAAI 2026 How Reasoning Influences Intersectional Biases in Vision–Language Models (Student Abstract) AAAI 2026 How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities EACL 2026