Image de couverture de livre

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Qi, Senmao, Zou, Yifei, Li, Peng, Lin, Ziyi, Cheng, Xiuzhen, Yu, Dongxiao
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
par: Sehwag, Udari Madhushani, et autres
Publié: (2026)

ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack
par: Lin, Xingwei, et autres
Publié: (2026)

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

Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking
par: Li, Yanzeng, et autres
Publié: (2025)

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
par: Zhang, Hanrong, et autres
Publié: (2024)

Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
par: Russinovich, Mark, et autres
Publié: (2024)

PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach
par: Lin, Zhihao, et autres
Publié: (2024)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
par: Zhu, Pengyu, et autres
Publié: (2025)

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs
par: Tan, Yixin, et autres
Publié: (2025)

Untargeted Jailbreak Attack
par: Huang, Xinzhe, et autres
Publié: (2025)

Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration
par: Tsmindashvili, Tatia, et autres
Publié: (2025)

Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models
par: Das, Badhan Chandra, et autres
Publié: (2026)

Invisible to Humans, Triggered by Agents: Stealthy Jailbreak Attacks on Mobile Vision-Language Agents
par: Ding, Renhua, et autres
Publié: (2025)

The Echo Chamber Multi-Turn LLM Jailbreak
par: Alobaid, Ahmad, et autres
Publié: (2026)

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

Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks
par: Tong, Haibo, et autres
Publié: (2025)

ToolTweak: An Attack on Tool Selection in LLM-based Agents
par: Sneh, Jonathan, et autres
Publié: (2025)

Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
par: Yan, Bingyu, et autres
Publié: (2025)

Free-MAD: Consensus-Free Multi-Agent Debate
par: Cui, Yu, et autres
Publié: (2025)

Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks
par: Zhang, Yingjie, et autres
Publié: (2025)

SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection
par: Shan, Zhengyang, et autres
Publié: (2026)

The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities
par: Litvak, Ron
Publié: (2026)

Web Fraud Attacks Against LLM-Driven Multi-Agent Systems
par: Kong, Dezhang, et autres
Publié: (2025)

Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks
par: Wu, ChenYu, et autres
Publié: (2025)

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers
par: Li, Xirui, et autres
Publié: (2024)

MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue
par: Wang, Fengxiang, et autres
Publié: (2024)

Involuntary Jailbreak: On Self-Prompting Attacks
par: Guo, Yangyang, et autres
Publié: (2025)

The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
par: Hossain, Ismail, et autres
Publié: (2026)

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
par: Saha, Shoumik, et autres
Publié: (2025)

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
par: Yu, Miao, et autres
Publié: (2024)

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

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
par: Cheng, Ruoxi, et autres
Publié: (2024)

From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
par: Zhang, Zhixiang, et autres
Publié: (2026)

Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
par: Yan, Yu, et autres
Publié: (2026)

Activation-Guided Local Editing for Jailbreaking Attacks
par: Wang, Jiecong, et autres
Publié: (2025)

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems
par: Jiao, Ruochen, et autres
Publié: (2024)

FlipAttack: Jailbreak LLMs via Flipping
par: Liu, Yue, et autres
Publié: (2024)

Efficient LLM Safety Evaluation through Multi-Agent Debate
par: Lin, Dachuan, et autres
Publié: (2025)

Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models
par: Hong, Wenjing, et autres
Publié: (2026)

MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
par: Zhang, Xinkai, et autres
Publié: (2026)