SHINE: Shielding Backdoors in Deep Reinforcement Learning

Zhuowen Yuan, Wenbo Guo, Jinyuan Jia, Bo Li, D. Song
2/12/2026

No official code found. Best implementation: eurekayuan/SHINE (5 stars, last commit 2024-07-28).

Semantic Scholar

Code Implementations(1)

eurekayuan/SHINECommunity66%

Official code for: "SHINE: Shielding Backdoors in Deep Reinforcement Learning"

52Shell, PythonJun 5, 20242 years ago

Similar Papers

PAGER: Accurate Failure Characterization in Deep Regression Models

100% match2026

FedInverse: Evaluating Privacy Leakage in Federated Learning

100% match2026

IBA: Towards Irreversible Backdoor Attacks in Federated Learning

99% match1 repo412026

TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks

99% match2026

PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques

99% match2026

pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation

99% match2026

Cite this paper

@article{yuan2026shine,
  title  = {SHINE: Shielding Backdoors in Deep Reinforcement Learning},
  author = {Zhuowen Yuan and Wenbo Guo and Jinyuan Jia and Bo Li and D. Song},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:5275aa3bd4a9f0837056705faaa87997bb75e77d},
  journal = {ICML 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/5275aa3bd4a9f0837056705faaa87997bb75e77d.svg)](https://codeofpaper.com/paper/5275aa3bd4a9f0837056705faaa87997bb75e77d)

Discussion