AI Safety

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency ICCV 2025 Jailbreaking? One Step Is Enough! ACL 2025 Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising CVPR 2025 Jailbreaking with Universal Multi-Prompts NAACL 2025 Jailbreak Large Vision-Language Models Through Multi-Modal Linkage ACL 2025 Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025 JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs ACL 2025 Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility EMNLP 2025 JailPO: A Novel Black-Box Jailbreak Framework via Preference Optimization Against Aligned LLMs AAAI 2025 J&H: Evaluating the Robustness of Large Language Models Under Knowledge-Injection Attacks in Legal Domain AAAI 2025 JU-CSE-NLP’25 at SemEval-2025 Task 4: Learning to Unlearn LLMs SemEval 2025 Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges ACL 2025 Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning ICML 2025 Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Textures ICCV 2025 Knowledge Boundary of Large Language Models: A Survey ACL 2025 Knowledge Graph Guided Evaluation of Abstention Techniques NAACL 2025 Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning ACL 2025 Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling ACL 2025 Lacuna Inc. at SemEval-2025 Task 4: LoRA-Enhanced Influence-Based Unlearning for LLMs SemEval 2025 Language Model Alignment in Multilingual Trolley Problems ICLR 2025 Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in Legislation ACL 2025 Language Models Identify Ambiguities and Exploit Loopholes EMNLP 2025 Language Models Learn to Mislead Humans via RLHF ICLR 2025 Language Models Resist Alignment: Evidence From Data Compression ACL 2025 Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis NAACL 2025