safety mechanism

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs ACL 2026 SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering ACL 2026 TVChain: Leveraging Textual-Visual Prompt Chains for Jailbreaking Large Vision-Language Models AAAI 2026 Agents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks ACL 2025 Assessing Vulnerabilities in State-of-the-Art Large Language Models Through Hex Injection (Student Abstract) AAAI 2025 Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities ACL 2025 Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models ICLR 2025 Distraction is All You Need for Multimodal Large Language Model Jailbreaking CVPR 2025 Guardrails, not Guidance: Understanding Responses to LGBTQ+ Language in Large Language Models NAACL 2025 HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States ACL 2025 Is Your Multimodal Language Model Oversensitive to Safe Queries? ICLR 2025 Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency ICCV 2025 Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025 LLMs for Translation: Historical, Low-Resourced Languages and Contemporary AI Models NAACL 2025 Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization IJCNLP 2025 PLA: Prompt Learning Attack against Text-to-Image Generative Models ICCV 2025 Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level ACL 2025 Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs ACL 2025 Small Changes, Big Impact: How Manipulating a Few Neurons Can Drastically Alter LLM Aggression ACL 2025 Sugar-Coated Poison: Benign Generation Unlocks Jailbreaking EMNLP 2025 Tongue-Tied: Breaking LLMs Safety Through New Language Learning NAACL 2025 VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models EMNLP 2025 What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs ACL 2025 Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models ECCV 2024 Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts ICML 2024