jailbreak attack

SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking ACL 2026 Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents ACL 2026 Towards Robust Multimodal Large Language Models Against Jailbreak Attacks CVPR 2026 TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration CVPR 2026 TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards ACL 2026 Unraveling LLM Jailbreaks Through Safety Knowledge Neurons EACL 2026 Unveiling AI Safety in Fine-tuning Quantized Model AAAI 2026 When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models ACL 2026 When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs’ Toxicity AAAI 2026 Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets ACL 2026 Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models EACL 2026 R^2-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning ICLR 2025 AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender EMNLP 2025 Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training EMNLP 2025 AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models ICLR 2025 AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models ACL 2025 AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents ICLR 2025 ALIS: Aligned LLM Instruction Security Strategy for Unsafe Input Prompt COLING 2025 A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos ACL 2025 An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks ICML 2025 A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns ACL 2025 Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment EMNLP 2025 Audio Is the Achilles’ Heel: Red Teaming Audio Large Multimodal Models NAACL 2025 AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs NAACL 2025 AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs ICLR 2025