jailbreaking attack

CHASE: Contextual History for Adaptive and Simple Exploitation in Large Language Model Jailbreaking AAAI 2026 Distractor-Based Jailbreaking Attacks in Language Models and Associated Changes in Chain-of-Thought Content (Student Abstract) AAAI 2026 Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak AAAI 2026 Reference Attack: A New Cross-Modal Jailbreaking Attack against Multimodal Large Language Models ACL 2026 TVChain: Leveraging Textual-Visual Prompt Chains for Jailbreaking Large Vision-Language Models AAAI 2026 AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs ICML 2025 An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer NAACL 2025 Distraction is All You Need for Multimodal Large Language Model Jailbreaking CVPR 2025 Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints ACL 2025 ImgTrojan: Jailbreaking Vision-Language Models with ONE Image NAACL 2025 Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks ICLR 2025 Jailbreaking with Universal Multi-Prompts NAACL 2025 ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs ICLR 2025 Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective COLING 2025 SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models EMNLP 2025 Security Attacks on LLM-based Code Completion Tools AAAI 2025 sudoLLM: On Multi-role Alignment of Language Models EMNLP 2025 Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond ICML 2025 Understanding and Enhancing the Transferability of Jailbreaking Attacks ICLR 2025 ColJailBreak: Collaborative Generation and Editing for Jailbreaking Text-to-Image Deep Generation NeurIPS 2024 Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization ACL 2024 Fight Back Against Jailbreaking via Prompt Adversarial Tuning NeurIPS 2024 Linguistic Obfuscation Attacks and Large Language Model Uncertainty EACL 2024 Many-shot Jailbreaking NeurIPS 2024 Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization NeurIPS 2024