Copertina

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Wentian, Xiang, Zhen, Niu, Wei, Guan, Le
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation
di: Liu, Zehao, et al.
Pubblicazione: (2025)

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
di: Wang, Zhaoqi, et al.
Pubblicazione: (2025)

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
di: Lin, Zheng, et al.
Pubblicazione: (2026)

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection
di: Debi, Tanusree, et al.
Pubblicazione: (2026)

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
di: Zhang, Chuhan, et al.
Pubblicazione: (2025)

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree
di: Johnson, Sam, et al.
Pubblicazione: (2025)

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
di: Saha, Shoumik, et al.
Pubblicazione: (2025)

The Echo Chamber Multi-Turn LLM Jailbreak
di: Alobaid, Ahmad, et al.
Pubblicazione: (2026)

Re-Triggering Safeguards within LLMs for Jailbreak Detection
di: Lin, Zheng, et al.
Pubblicazione: (2026)

The Great Pretender: A Stochasticity Problem in LLM Jailbreak
di: Monteuuis, Jean-Philippe, et al.
Pubblicazione: (2026)

EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models via Equation Solving and Code Completion
di: Liang, Zhen, et al.
Pubblicazione: (2025)

GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models
di: Mia, Md Jueal, et al.
Pubblicazione: (2026)

Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services
di: Sun, Guoheng, et al.
Pubblicazione: (2025)

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
di: Huang, Yao, et al.
Pubblicazione: (2025)

"To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios
di: Sun, Zhen, et al.
Pubblicazione: (2025)

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage
di: Dong, Xiaoning, et al.
Pubblicazione: (2024)

Token-Efficient Prompt Injection Attack: Provoking Cessation in LLM Reasoning via Adaptive Token Compression
di: Cui, Yu, et al.
Pubblicazione: (2025)

PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach
di: Lin, Zhihao, et al.
Pubblicazione: (2024)

OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
di: Wang, Longxiang, et al.
Pubblicazione: (2026)

Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration
di: Tsmindashvili, Tatia, et al.
Pubblicazione: (2025)

Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks
di: Geng, Jianing, et al.
Pubblicazione: (2025)

FlipAttack: Jailbreak LLMs via Flipping
di: Liu, Yue, et al.
Pubblicazione: (2024)

New Wide-Net-Casting Jailbreak Attacks Risk Large Models
di: Xiang, Qiuchi, et al.
Pubblicazione: (2026)

Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks
di: Wu, ChenYu, et al.
Pubblicazione: (2025)

Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks
di: Zhang, Yingjie, et al.
Pubblicazione: (2025)

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate
di: Qi, Senmao, et al.
Pubblicazione: (2025)

Enhancing Jailbreak Attacks on LLMs via Persona Prompts
di: Zhang, Zheng, et al.
Pubblicazione: (2025)

NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks
di: Asl, Javad Rafiei, et al.
Pubblicazione: (2025)

CCFC: Core & Core-Full-Core Dual-Track Defense for LLM Jailbreak Protection
di: Hu, Jiaming, et al.
Pubblicazione: (2025)

Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
di: Russinovich, Mark, et al.
Pubblicazione: (2024)

Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses
di: Shang, Zhengchun, et al.
Pubblicazione: (2025)

The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
di: Hossain, Ismail, et al.
Pubblicazione: (2026)

AiRacleX: Automated Detection of Price Oracle Manipulations via LLM-Driven Knowledge Mining and Prompt Generation
di: Gao, Bo, et al.
Pubblicazione: (2025)

Untargeted Jailbreak Attack
di: Huang, Xinzhe, et al.
Pubblicazione: (2025)

LLM Jailbreak Detection for (Almost) Free!
di: Chen, Guorui, et al.
Pubblicazione: (2025)

Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack
di: Kang, Daewon, et al.
Pubblicazione: (2025)

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
di: Mu, Junjie, et al.
Pubblicazione: (2025)

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs
di: Chen, Wenyu, et al.
Pubblicazione: (2026)

VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
di: Nie, Yuzhou, et al.
Pubblicazione: (2025)

SafeDream: Safety World Model for Proactive Early Jailbreak Detection
di: Yan, Bo, et al.
Pubblicazione: (2026)