Stealthy data poisoning attack method on offline reinforcement learning in unmanned systems
Aiming at the limitations in effectiveness and stealth of existing offline reinforcement learning(RL) data poisoning attacks, a critical time-step dynamic poisoning attack was proposed, perturbing important samples to achieve efficient and covert attacks. Temporal difference errors, identified throu...
Saved in:
Main Authors: | ZHOU Xue, MAN Dapeng, XU Chen, LYU Jiguang, ZENG Fanyi, GAO Chaoyang, YANG Wu |
---|---|
Format: | Article |
Language: | zho |
Published: |
Editorial Department of Journal on Communications
2024-12-01
|
Series: | Tongxin xuebao |
Subjects: | |
Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024264/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Data poisoning attack detection approach for quality of service aware cloud API recommender system
by: Zhen CHEN, et al.
Published: (2023-08-01) -
Research on HTML5 application cache poison attack
by: Yan JIA, et al.
Published: (2016-10-01) -
Gradient purification federated adaptive learning algorithm for Byzantine attack resistance
by: YANG Hui, et al.
Published: (2024-10-01) -
Offline prompt reinforcement learning method based on feature extraction
by: Tianlei Yao, et al.
Published: (2025-01-01) -
Moor: Model-based offline policy optimization with a risk dynamics model
by: Xiaolong Su, et al.
Published: (2024-11-01)