Training A Secure Model Against Data-Free Model Extraction

Zhenyi Wang, Li Shen, Junfeng Guo, Tiehang Duan, Siyu Luan +2 more
2/14/2026

No official code found. Best implementation: AdeebaRafi/The-Trickster-Defense (0 stars, last commit 2025-12-26).

DOISemantic Scholar

Code Implementations(1)

AdeebaRafi/The-Trickster-DefenseCommunity60%

A Simple Demo Against Model Theft: This is a small, educational project I built to understand the concept of Model Extraction Attacks and how to defend against them. The code demonstrates a "Trickster Defense" mechanism, inspired by the research paper "Training A Secure Model Against Data-Free Model Extraction".

00Jupyter NotebookSep 14, 20259 months ago

Cite this paper

@article{wang2026training,
  title  = {Training A Secure Model Against Data-Free Model Extraction},
  author = {Zhenyi Wang and Li Shen and Junfeng Guo and Tiehang Duan and Siyu Luan and Tongliang Liu and Mingchen Gao},
  year   = {2026},
  doi    = {10.1007/978-3-031-72986-7_19},
  url    = {https://doi.org/10.1007/978-3-031-72986-7_19},
  journal = {ECCV 2024 2024}
}

Discussion