Image de couverture de livre

Let the Bees Find the Weak Spots: A Path Planning Perspective on Multi-Turn Jailbreak Attacks against LLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Yize, Hou, Yunyun, Sui, Aina
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks
par: Gibbs, Tom, et autres
Publié: (2024)

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
par: Ying, Zonghao, et autres
Publié: (2025)

Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
par: Hu, Hanjiang, et autres
Publié: (2025)

Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
par: Xu, Zhao, et autres
Publié: (2024)

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
par: Shen, Guobin, et autres
Publié: (2025)

One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs
par: Li, Linbao, et autres
Publié: (2025)

RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking
par: Jiang, Yifan, et autres
Publié: (2024)

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
par: Chen, Yunhao, et autres
Publié: (2025)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
par: Zeng, Yifan, et autres
Publié: (2024)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
par: Liu, Fan, et autres
Publié: (2024)

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
par: Huang, Caishuang, et autres
Publié: (2024)

Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors
par: Zhao, Yi, et autres
Publié: (2025)

Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs
par: Li, Xiang, et autres
Publié: (2025)

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
par: Wang, Yidan, et autres
Publié: (2025)

Proactive defense against LLM Jailbreak
par: Zhao, Weiliang, et autres
Publié: (2025)

Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs
par: Pu, Rui, et autres
Publié: (2024)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
par: Chu, Junjie, et autres
Publié: (2024)

JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
par: Luo, Weidi, et autres
Publié: (2024)

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
par: Hu, Xiaomeng, et autres
Publié: (2025)

ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs
par: Ni, Ziyi, et autres
Publié: (2025)

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs
par: Akbar-Tajari, Mohammad, et autres
Publié: (2025)

Mitigating Jailbreaks with Intent-Aware LLMs
par: Yeo, Wei Jie, et autres
Publié: (2025)

Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
par: Tu, Shangqing, et autres
Publié: (2024)

FlexLLM: Exploring LLM Customization for Moving Target Defense on Black-Box LLMs Against Jailbreak Attacks
par: Chen, Bocheng, et autres
Publié: (2024)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
par: Xu, Zhangchen, et autres
Publié: (2024)

Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search
par: Zhou, Andy, et autres
Publié: (2025)

What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
par: Kirch, Nathalie, et autres
Publié: (2024)

Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks
par: Gohil, Vasudev
Publié: (2025)

Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
par: Zhang, Chiyu, et autres
Publié: (2025)

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
par: Li, Nathaniel, et autres
Publié: (2024)

AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs
par: Lv, Lijia, et autres
Publié: (2024)

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
par: Kadali, Sri Durga Sai Sowmya, et autres
Publié: (2026)

A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
par: Luo, Xuan, et autres
Publié: (2025)

Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models
par: Nihal, Ragib Amin, et autres
Publié: (2025)

Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models
par: Dong, Yiting, et autres
Publié: (2024)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
par: Jiang, Tanqiu, et autres
Publié: (2024)

Chain-of-Lure: A Universal Jailbreak Attack Framework using Unconstrained Synthetic Narratives
par: Chang, Wenhan, et autres
Publié: (2025)

HSF: Defending against Jailbreak Attacks with Hidden State Filtering
par: Qian, Cheng, et autres
Publié: (2024)

Well, that escalated quickly: The Single-Turn Crescendo Attack (STCA)
par: Aqrawi, Alan, et autres
Publié: (2024)

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
par: Rando, Javier, et autres
Publié: (2024)