Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
jinhaibo 7aecf6cb7c | 1 year ago | |
---|---|---|
CycleGAN | 1 year ago | |
README.md | 1 year ago | |
detoxification.py | 1 year ago | |
implement.py | 1 year ago | |
neuron_detection.py | 1 year ago | |
retrain.py | 1 year ago | |
run.sh | 1 year ago | |
run_re.py | 1 year ago | |
train.py | 1 year ago |
This is the repository for DFST paper Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification.
See https://arxiv.org/abs/2012.11212.
Python3.6, tensorflow=1.13.1, keras=2.2.4, numpy, pickle, PIL.
Note that currently we only provide codes on VGG and CIFAR-10 and the attack target label is 0.
Create some folders: ./dataset
, ./model
, ./weights
.
Download CIFAR-10 dataset and re-define it in the follwing format:
Save the dictionaries in cifar_train
and cifar_test
file in ./dataset
using pickle.
pickle.dump(cifar_train, open('./dataset/cifar_train', 'wb'))
pickle.dump(cifar_test, open('./dataset/cifar_test', 'wb'))
Download sunrise images from Weather-Dataset into ./CycleGAN/sunrise
.
Type in cd CycleGAN
.
Train your own Cycle GAN python CycleGAN.py
.
Poison the training dataset python data_poisoning.py
.
Train a benign VGG as a classifier on CIFAR-10 python train.py
.
Inject the trigger using poisoned training data python retrain.py
.
Perform detoxification to force the model to learn deep features sh run.sh
.
Free to contact the author cheng535@purdue.edu.
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》