You Can't Fool All the Models: Detect Adversarial Samples via Pruning Models

Renxuan Wang, Zuohui Chen, Hui Dong, Qi Xuan

BibTeX
@inproceedings{wang2021you,
  author = {Renxuan Wang and Zuohui Chen and Hui Dong and Qi Xuan},
  title = {{You Can't Fool All the Models: Detect Adversarial Samples via Pruning Models}},
  booktitle = {IEEE Access},
  year = {2021},
  url = {https://openreview.net/forum?id=7Qwd3oBTQv},
}

Loading related content...

Figure