AI Safety

DialogGuard: Multi-Agent Psychosocial Safety Evaluation Interface of Sensitive LLM Responses ACL 2026 Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs CVPR 2026 Differentiated Directional Intervention: A Framework for Evading LLM Safety Alignment AAAI 2026 DIFT: Protecting Contrastive Learning Against Data Poisoning Backdoor Attacks AAAI 2026 Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security AAAI 2026 Distilling Safe LLM Systems via Soft Prompts for On Device Settings UAI 2026 Distractor-Based Jailbreaking Attacks in Language Models and Associated Changes in Chain-of-Thought Content (Student Abstract) AAAI 2026 DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation EACL 2026 Diversifying Counterattacks: Orthogonal Exploration for Robust CLlP Inference AAAI 2026 DoBlock: Blocking Malicious Association Propagation for Backdoor-Robust Federated Learning Under Domain Skew AAAI 2026 Do Large Language Models Reflect Demographic Pluralism in Safety? EACL 2026 Do LLM hallucination detectors suffer from low-resource effect? EACL 2026 Domain Generalizable AI Guardrails with Augmented Policy Training ACL 2026 Don’t Judge a Book by its Cover: Testing LLMs’ Robustness Under Logical Obfuscation EACL 2026 Dormant Backdoor: Weaponizing Model Finetuning for Feasible Backdoor Attacks Against Pretrained Models AAAI 2026 Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment AAAI 2026 Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure AAAI 2026 DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection EACL 2026 DUP: Detection-guided Unlearning for Backdoor Purification in Language Models AAAI 2026 Dynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMs AAAI 2026 EASE: Practical and Efficient Safety Alignment for Small Language Models AAAI 2026 EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment CVPR 2026 EduGuardBench: A Holistic Benchmark for Evaluating the Pedagogical Fidelity and Adversarial Safety of LLMs as Simulated Teachers AAAI 2026 Efficient Hallucination Detection: Adaptive Bayesian Estimation of Semantic Entropy with Guided Semantic Exploration AAAI 2026 Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak AAAI 2026