AI Safety

Misalignment from Treating Means as Ends AAAI 2026 Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering AAAI 2026 Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy ACL 2026 Mitigating Self-Preference by Authorship Obfuscation AAAI 2026 MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control AAAI 2026 Model-Agnostic Sentiment Distribution Stability Analysis for Robust LLM-Generated Texts Detection AAAI 2026 Model Editing as a Double-Edged Sword: Steering Agent Behavior Toward Beneficence or Harm AAAI 2026 Modeling Human Adversarial Strategy Adaptation in Multi-Turn Language Model Interactions CoNLL 2026 Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints CVPR 2026 Modulation-Based Backdoors: Leveraging Amplitude and Frequency Patterns to Attack Speaker Recognition AAAI 2026 Moral Change or Noise? On Problems of Aligning AI with Temporally Unstable Human Feedback AAAI 2026 MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning AAAI 2026 MovieGraph-ToM: Evaluating Long-Range Theory of Mind in Large Language Models via Implicit Social-Causal Graphs AAAI 2026 MPMA: Preference Manipulation Attack Against Model Context Protocol AAAI 2026 MTAttack: Multi-Target Backdoor Attacks Against Large Vision-Language Models AAAI 2026 Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models AAAI 2026 Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation AAAI 2026 NaturalSloth: Revisiting Denial-of-Service Attacks on Large Language Models ACL 2026 Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models CVPR 2026 Now You Hear Me: Audio Narrative Attacks Against Large Audio–Language Models EACL 2026 NP-Hard Lower Bound Complexity for Semantic Self-Verification EACL 2026 Obedience or Vigilance? How Large Language Models React to Malicious Multiple-Choice Options (Student Abstract) AAAI 2026 Online Adaptive Probabilistic Safety Certificate with Language Guidance L4DC 2026 On Robustness of Linear Classifiers to Targeted Data Poisoning AAAI 2026 On Stealing Graph Neural Network Models AAAI 2026