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

Zhenyi Wang, Li Shen, Tongliang Liu, Tiehang Duan, Yanjun Zhu +3 more
2/12/2026

No official code found. Best implementation: joey-wang123/DFME-DRO (6 stars, last commit 2024-07-06).

DOISemantic Scholar

Code Implementations(1)

joey-wang123/DFME-DROCommunity57%

Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training (NeurIPS 2023)

61PythonJun 12, 20242 years ago

Similar Papers

Defense against Model Extraction Attack by Bayesian Active Watermarking

96% match1 repo62026

Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication

95% match1 repo32026

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

92% match1 repo112026

Robust Neural Contextual Bandit against Adversarial Corruptions

91% match2026

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

90% match1 repo132026

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

90% match1 repo142026

Cite this paper

@article{wang2026defending,
  title  = {Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training},
  author = {Zhenyi Wang and Li Shen and Tongliang Liu and Tiehang Duan and Yanjun Zhu and Dongling Zhan and D. Doermann and Mingchen Gao},
  year   = {2026},
  doi    = {10.52202/075280-0029},
  url    = {https://doi.org/10.52202/075280-0029},
  journal = {NEURIPS 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/114c2f2cc2ab8a80a6229339a0c532ff4d59caed.svg)](https://codeofpaper.com/paper/114c2f2cc2ab8a80a6229339a0c532ff4d59caed)

Discussion