Image de couverture de livre

TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yoon, Sung-Hoon, Qian, Ruizhi, Zhao, Minda, Li, Weiyue, Wang, Mengyu
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

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

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

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
par: Mehrotra, Anay, et autres
Publié: (2023)

"Moralized" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks
par: Wang, Libo
Publié: (2024)

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

Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
par: Zhu, Xiaoyuan, et autres
Publié: (2025)

LLM Jailbreak Detection for (Almost) Free!
par: Chen, Guorui, et autres
Publié: (2025)

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

Subtoxic Questions: Dive Into Attitude Change of LLM's Response in Jailbreak Attempts
par: Zhang, Tianyu, et autres
Publié: (2024)

Geneshift: Impact of different scenario shift on Jailbreaking LLM
par: Wu, Tianyi, et autres
Publié: (2025)

Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents
par: Das, Saswat, et autres
Publié: (2025)

Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
par: Wang, Zhaoqi, et autres
Publié: (2025)

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

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
par: Domico, Kyle, et autres
Publié: (2025)

Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models
par: Li, Yakai, et autres
Publié: (2025)

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

PAL: Proxy-Guided Black-Box Attack on Large Language Models
par: Sitawarin, Chawin, et autres
Publié: (2024)

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

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage
par: Dong, Xiaoning, et autres
Publié: (2024)

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

Transferable & Stealthy Ensemble Attacks: A Black-Box Jailbreaking Framework for Large Language Models
par: Yang, Yiqi, 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)

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

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
par: Xing, Wenpeng, et autres
Publié: (2025)

Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models
par: Huang, Chung-ju, et autres
Publié: (2026)

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

Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation
par: Schwartz, Daniel, et autres
Publié: (2025)

Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks
par: Kabir, Md Rysul, et autres
Publié: (2026)

Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models
par: Chen, Zhuo, et autres
Publié: (2024)

JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models
par: Ran, Delong, et autres
Publié: (2024)

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models
par: Zhao, Wei, et autres
Publié: (2024)

Defending against Jailbreak through Early Exit Generation of Large Language Models
par: Zhao, Chongwen, et autres
Publié: (2024)

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility
par: Murphy, Brendan, et autres
Publié: (2025)

TombRaider: Entering the Vault of History to Jailbreak Large Language Models
par: Ding, Junchen, et autres
Publié: (2025)

AdvPrefix: An Objective for Nuanced LLM Jailbreaks
par: Zhu, Sicheng, et autres
Publié: (2024)

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
par: Zhao, Shiji, et autres
Publié: (2025)

BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models
par: Wang, Xinyuan, et autres
Publié: (2024)

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

Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
par: Zhao, Jiawei, et autres
Publié: (2024)

Kov: Transferable and Naturalistic Black-Box LLM Attacks using Markov Decision Processes and Tree Search
par: Moss, Robert J.
Publié: (2024)