Image de couverture de livre

Collapsing Sequence-Level Data-Policy Coverage via Poisoning Attack in Offline Reinforcement Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhou, Xue, Man, Dapeng, Xu, Chen, Zeng, Fanyi, Liu, Tao, Wang, Huan, He, Shucheng, Gao, Chaoyang, Yang, Wu
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
par: Xu, Yinglun, et autres
Publié: (2024)

Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning
par: Liu, Shijie, et autres
Publié: (2025)

Hiding Backdoors within Event Sequence Data via Poisoning Attacks
par: Ermilova, Alina, et autres
Publié: (2023)

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling
par: Xu, Jiawei, et autres
Publié: (2024)

Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices
par: Woo, Jiin, et autres
Publié: (2024)

Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
par: Lobo, Elita, et autres
Publié: (2024)

Dataset Poisoning Attacks on Behavioral Cloning Policies
par: Kalra, Akansha, et autres
Publié: (2025)

Optimal Perturbation Budget Allocation for Data Poisoning in Offline Reinforcement Learning
par: Qiu, Junnan, et autres
Publié: (2025)

Offline Constrained Reinforcement Learning under Partial Data Coverage
par: Ko, Seokmin, et autres
Publié: (2025)

Sharpness-Aware Data Poisoning Attack
par: He, Pengfei, et autres
Publié: (2023)

Sybil-based Virtual Data Poisoning Attacks in Federated Learning
par: Zhu, Changxun, et autres
Publié: (2025)

Provable Watermarking for Data Poisoning Attacks
par: Zhu, Yifan, et autres
Publié: (2025)

Policy Constraint by Only Support Constraint for Offline Reinforcement Learning
par: Gao, Yunkai, et autres
Publié: (2025)

From Human Speech to Ocean Signals: Transferring Speech Large Models for Underwater Acoustic Target Recognition
par: Huang, Mengcheng, et autres
Publié: (2026)

Defending Against Neural Network Model Inversion Attacks via Data Poisoning
par: Zhou, Shuai, et autres
Publié: (2024)

Model-Based Offline Reinforcement Learning with Reliability-Guaranteed Sequence Modeling
par: He, Shenghong
Publié: (2025)

Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning
par: Liu, Tao, et autres
Publié: (2024)

ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization
par: Yang, Letian, et autres
Publié: (2026)

Trajectory-Level Data Augmentation for Offline Reinforcement Learning
par: Schmähling, Tobias, et autres
Publié: (2026)

Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
par: Liu, Tenglong, et autres
Publié: (2024)

Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning
par: Gao, Chen-Xiao, et autres
Publié: (2025)

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
par: Nguyen, Thanh, et autres
Publié: (2024)

Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
par: Zhang, Guangsheng, et autres
Publié: (2026)

PoiCGAN: A Targeted Poisoning Based on Feature-Label Joint Perturbation in Federated Learning
par: Liu, Tao, et autres
Publié: (2026)

To Switch or Not to Switch? Balanced Policy Switching in Offline Reinforcement Learning
par: Ma, Tao, et autres
Publié: (2024)

Logits Poisoning Attack in Federated Distillation
par: Tang, Yuhan, et autres
Publié: (2024)

Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
par: Zhang, Tianle, et autres
Publié: (2024)

Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data
par: Baumgärtner, Tim, et autres
Publié: (2024)

Data Poisoning Attacks to Local Differential Privacy Protocols for Graphs
par: He, Xi, et autres
Publié: (2024)

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization
par: Lei, Kun, et autres
Publié: (2023)

Data Poisoning Attacks in Gossip Learning
par: Pham, Alexandre, et autres
Publié: (2024)

Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs
par: Kong, Jiawei, et autres
Publié: (2025)

Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data
par: Madhow, Sunil, et autres
Publié: (2023)

Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
par: Zhang, Haichao, et autres
Publié: (2023)

Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning
par: Liu, Tao, et autres
Publié: (2025)

Online Poisoning Attack Against Reinforcement Learning under Black-box Environments
par: Li, Jianhui, et autres
Publié: (2024)

Policy-regularized Offline Multi-objective Reinforcement Learning
par: Lin, Qian, et autres
Publié: (2024)

Local Environment Poisoning Attacks on Federated Reinforcement Learning
par: Ma, Evelyn, et autres
Publié: (2023)

On the Complexity of Offline Reinforcement Learning with $Q^\star$-Approximation and Partial Coverage
par: Liu, Haolin, et autres
Publié: (2026)

Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
par: Xu, Yuancheng, et autres
Publié: (2024)