When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Xuan, Nie, Yuzhou, Guo, Wenbo, Zhang, Xiangyu
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs
di: Chen, Xuan, et al.
Pubblicazione: (2024)

A DRL-Empowered Multi-Level Jamming Approach for Secure Semantic Communication
di: Chen, Weixuan, et al.
Pubblicazione: (2025)

TBDD: A New Trust-based, DRL-driven Framework for Blockchain Sharding in IoT
di: Zhang, Zixu, et al.
Pubblicazione: (2024)

Backdoors in DRL: Four Environments Focusing on In-distribution Triggers
di: Ashcraft, Chace, et al.
Pubblicazione: (2025)

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

Carbon-Aware Intrusion Detection: A Comparative Study of Supervised and Unsupervised DRL for Sustainable IoT Edge Gateways
di: Jamshidi, Saeid, et al.
Pubblicazione: (2025)

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage
di: Nie, Yuzhou, et al.
Pubblicazione: (2024)

MalwarePT: A Binary-Level Foundation Model for Malware Analysis
di: Vasan, Saastha, et al.
Pubblicazione: (2026)

Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security
di: Kim, Hajun, et al.
Pubblicazione: (2025)

AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
di: Wang, Zhun, et al.
Pubblicazione: (2025)

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

HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking
di: Wang, Zeng, et al.
Pubblicazione: (2026)

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking
di: Zhang, Junke, et al.
Pubblicazione: (2026)

Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
di: Xiong, Chen, et al.
Pubblicazione: (2024)

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
di: Chen, Xuan, et al.
Pubblicazione: (2025)

MacPrompt: Maraconic-guided Jailbreak against Text-to-Image Models
di: Ye, Xi, et al.
Pubblicazione: (2026)

Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety
di: Chen, Xuan, et al.
Pubblicazione: (2026)

MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection
di: Chen, Xuan, et al.
Pubblicazione: (2026)

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

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

FlexLLM: Exploring LLM Customization for Moving Target Defense on Black-Box LLMs Against Jailbreak Attacks
di: Chen, Bocheng, et al.
Pubblicazione: (2024)

The Forking Way: When TEEs Meet Consensus
di: Wilde, Annika, et al.
Pubblicazione: (2024)

PrivCode: When Code Generation Meets Differential Privacy
di: Liu, Zheng, et al.
Pubblicazione: (2025)

SpatialJB: How Text Distribution Art Becomes the "Jailbreak Key" for LLM Guardrails
di: Mou, Zhiyi, et al.
Pubblicazione: (2026)

Beyond Jailbreak: Unveiling Risks in LLM Applications Arising from Blurred Capability Boundaries
di: Zhang, Yunyi, et al.
Pubblicazione: (2025)

Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
di: Dong, Yingkai, et al.
Pubblicazione: (2024)

Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking
di: Wu, Yu-Hang, et al.
Pubblicazione: (2025)

JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit
di: He, Zeqing, et al.
Pubblicazione: (2024)

TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization
di: Wang, Yanting, et al.
Pubblicazione: (2025)

Belt and Braces: When Federated Learning Meets Differential Privacy
di: Ren, Xuebin, et al.
Pubblicazione: (2024)

Adaptive Probe-based Steering for Robust LLM Jailbreaking
di: Chen, Junxi, et al.
Pubblicazione: (2026)

When AI Meets Wall Street: A Survey on Trustworthy AI in Fintech
di: Zeng, Qingwen, et al.
Pubblicazione: (2026)

When Graph Convolution Meets Double Attention: Online Privacy Disclosure Detection with Multi-Label Text Classification
di: Liang, Zhanbo, et al.
Pubblicazione: (2023)

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

AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens
di: Lu, Lin, et al.
Pubblicazione: (2024)

Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense
di: Chen, Zejian, et al.
Pubblicazione: (2026)

Defending Jailbreak Prompts via In-Context Adversarial Game
di: Zhou, Yujun, et al.
Pubblicazione: (2024)

Proactive defense against LLM Jailbreak
di: Zhao, Weiliang, et al.
Pubblicazione: (2025)

When Machine Learning Meets Vulnerability Discovery: Challenges and Lessons Learned
di: Arasteh, Sima, et al.
Pubblicazione: (2025)

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
di: Zhao, Weixiang, et al.
Pubblicazione: (2025)