SCccc21 / Knowledge-Enriched-DMI

MIT License
41 stars 11 forks source link

Knowledge-Enriched-Distributional-Model-Inversion-Attacks

This is a PyTorch implementation of our paper at ICCV2021:

Knowledge Enriched Distributional Model Inversion Attacks [paper] [arxiv]

We propose a novel 'Inversion-Specific GAN' that can better distill knowledge useful for performing attacks on private models from public data. Moreover, we propose to model a private data distribution for each target class which refers to 'Distributional Recovery'.

Requirement

This code has been tested with Python 3.6, PyTorch 1.0 and cuda 10.0.

Getting Started

Build a inversion-specific GAN

Distributional Recovery

Run python recovery.py

Reference

[1] Zhang, Yuheng, et al. "The secret revealer: Generative model-inversion attacks against deep neural networks." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020.