model safety

A Robust Unlearning Method with Adaptive Knowledge Guidance and Memory Preservation AAAI 2026 Distractor-Based Jailbreaking Attacks in Language Models and Associated Changes in Chain-of-Thought Content (Student Abstract) AAAI 2026 Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory CVPR 2026 Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs AAAI 2026 Safeguarding Language Models via Self-Destruct Trapdoor EACL 2026 Safe Vision-Language Models via Unsafe Weights Manipulation WACV 2026 Towards Inclusive AI: Advancing Multilingual Large Language Models AAAI 2026 Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks AAAI 2026 Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position AAAI 2026 AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender EMNLP 2025 Advancing Intelligent Software Development and Trustworthy Models Through the Synergy of Software Engineering and LLMs AAAI 2025 Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-Agent EMNLP 2025 AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders EMNLP 2025 A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos ACL 2025 An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer NAACL 2025 AraTrust: An Evaluation of Trustworthiness for LLMs in Arabic COLING 2025 Attention Tracker: Detecting Prompt Injection Attacks in LLMs NAACL 2025 Automating Steering for Safe Multimodal Large Language Models EMNLP 2025 Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms ACL 2025 Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space ACL 2025 Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet ACL 2025 CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations ACL 2025 Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models EMNLP 2025 Dynamic Evil Score-Guided Decoding: An Efficient Decoding Framework For Red-Team Model ACL 2025 Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack ACL 2025