Imagen de Portada

Policy Disruption in Reinforcement Learning:Adversarial Attack with Large Language Models and Critical State Identification

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiang, Junyong, Tian, Buwei, Xu, Chenxing, Li, Songze, Dong, Lu
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective
por: Duan, Tianyang, et al.
Publicado: (2025)

Off-Policy Value-Based Reinforcement Learning for Large Language Models
por: Wang, Peng-Yuan, et al.
Publicado: (2026)

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
por: Zhang, Mingxuan, et al.
Publicado: (2025)

Dynamic Adversarial Reinforcement Learning for Robust Multimodal Large Language Models
por: Bao, Yicheng, et al.
Publicado: (2026)

Sampling-aware Adversarial Attacks Against Large Language Models
por: Beyer, Tim, et al.
Publicado: (2025)

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
por: Nguyen, Thanh, et al.
Publicado: (2024)

Adversarial Reinforcement Learning for Large Language Model Agent Safety
por: Wang, Zizhao, et al.
Publicado: (2025)

Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach
por: Lu, Ziqing, et al.
Publicado: (2025)

MSfusion: A Dynamic Model Splitting Approach for Resource-Constrained Machines to Collaboratively Train Larger Models
por: Xie, Jin, et al.
Publicado: (2024)

Reinforcement Learning with Promising Tokens for Large Language Models
por: Pang, Jing-Cheng, et al.
Publicado: (2026)

Adversarial Contrastive Learning for LLM Quantization Attacks
por: Song, Dinghong, et al.
Publicado: (2026)

TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning
por: Li, Ge, et al.
Publicado: (2024)

The Resurgence of GCG Adversarial Attacks on Large Language Models
por: Tan, Yuting, et al.
Publicado: (2025)

Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
por: Yao, Duanyi, et al.
Publicado: (2024)

Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
por: Li, Songze, et al.
Publicado: (2026)

Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise
por: Lian, Puwei, et al.
Publicado: (2026)

Enhancing Membership Inference Attacks on Diffusion Models from a Frequency-Domain Perspective
por: Lian, Puwei, et al.
Publicado: (2025)

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
por: Sun, Ye, et al.
Publicado: (2026)

DiffPoGAN: Diffusion Policies with Generative Adversarial Networks for Offline Reinforcement Learning
por: Hu, Xuemin, et al.
Publicado: (2024)

URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
por: Yao, Duanyi, et al.
Publicado: (2024)

Adversarial Evasion Attack Efficiency against Large Language Models
por: Vitorino, João, et al.
Publicado: (2024)

Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
por: Li, Simin, et al.
Publicado: (2023)

Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy
por: Zheng, Xiang, et al.
Publicado: (2023)

Beyond Suffixes: Token Position in GCG Adversarial Attacks on Large Language Models
por: Eddoubi, Hicham, et al.
Publicado: (2026)

REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective
por: Geisler, Simon, et al.
Publicado: (2025)

Adversarial Inception Backdoor Attacks against Reinforcement Learning
por: Rathbun, Ethan, et al.
Publicado: (2024)

Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent
por: Biswas, Sajib, et al.
Publicado: (2025)

TernaryLLM: Ternarized Large Language Model
por: Chen, Tianqi, et al.
Publicado: (2024)

Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning
por: Wei, Honghao, et al.
Publicado: (2024)

Mildly Constrained Evaluation Policy for Offline Reinforcement Learning
por: Xu, Linjie, et al.
Publicado: (2023)

ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts
por: Pang, Jing-Cheng, et al.
Publicado: (2025)

Causal Policy Learning in Reinforcement Learning: Backdoor-Adjusted Soft Actor-Critic
por: Vo, Thanh Vinh, et al.
Publicado: (2025)

ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
por: Li, Ziniu, et al.
Publicado: (2023)

POLAR: Policy-based Layerwise Reinforcement Learning Method for Stealthy Backdoor Attacks in Federated Learning
por: Yu, Kuai, et al.
Publicado: (2025)

Towards Client Driven Federated Learning
por: Li, Songze, et al.
Publicado: (2024)

FedMeS: Personalized Federated Continual Learning Leveraging Local Memory
por: Xie, Jin, et al.
Publicado: (2024)

Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
por: Winninger, Thomas, et al.
Publicado: (2025)

Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
por: Wang, Yubo, et al.
Publicado: (2024)

AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models
por: Yeh, Cheng-Kai, et al.
Publicado: (2025)

Box Thirding: Anytime Best Arm Identification under Insufficient Sampling
por: Hwang, Seohwa, et al.
Publicado: (2026)