Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication

Yanchao Sun, Ruijie Zheng, Parisa Hassanzadeh, Yongyuan Liang, S. Feizi +2 more
2/12/2026

No official code found. Best implementation: umd-huang-lab/cmarl_ame (3 stars, last commit 2023-02-28).

Semantic Scholar

Code Implementations(1)

umd-huang-lab/cmarl_ameCommunity60%

Implementation of ICLR'23 publication "Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication".

33Shell, PythonFeb 28, 20233 years ago

Similar Papers

Robust Neural Contextual Bandit against Adversarial Corruptions

96% match2026

Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks

96% match1 repo112026

Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training

95% match1 repo62026

FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning

94% match1 repo132026

GAN You See Me? Enhanced Data Reconstruction Attacks against Split Inference

94% match1 repo142026

Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing

91% match2026

Cite this paper

@article{sun2026certifiably,
  title  = {Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication},
  author = {Yanchao Sun and Ruijie Zheng and Parisa Hassanzadeh and Yongyuan Liang and S. Feizi and Sumitra Ganesh and Furong Huang},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:4678c9f7ce7d91bc1770e64856b4ab9e050af2e2},
  journal = {ICLR 2023 2023}
}

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/4678c9f7ce7d91bc1770e64856b4ab9e050af2e2.svg)](https://codeofpaper.com/paper/4678c9f7ce7d91bc1770e64856b4ab9e050af2e2)

Discussion