Description:
This is the official repository for the implementation of DeepConfuse.
A pytorch implementation of DeepConfuse proposed in "Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder". This repo contains pretrained model and our code for experiment results on MNIST, CIFAR-10 and a restrict version of ImageNet. The implementation is flexible enough for modifying the model and applying it to your own datasets.
Package Official Website:
http://www.lamda.nju.edu.cn/code_deepconfuse.ashxPackage Github Website:
https://github.com/kingfengji/DeepConfuseATTN: This package is provided "AS IS" and free for academic usage. You can run it at your own risk. For other purposes, please contact Prof. Zhi-Hua Zhou (
zhouzh@lamda.nju.edu.cn).
ATTN2: This package was developed and maintained by Mr.Ji Feng (
http://www.lamda.nju.edu.cn/fengj/). For any problem concerning the codes, please feel free to contact Mr.Feng. (
fengj@lamda.nju.edu.cn)
Reference: [1] J. Feng，Q.-Z. Cai and Z.-H. Zhou. "Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder" In: NeurIPS, 2019
Download:
code (32.2MB)