Open jiequancui opened 3 years ago
I don't see the implementation of the robust-ml API. Am I looking in the wrong place?
Hi, are there some examples for PyTorch to implement with robust-ml API?
You can see a bunch of examples here: https://www.robust-ml.org/defenses/. Here is one that uses torch: https://github.com/bethgelab/AnalysisBySynthesis. The robust-ml API is independent of the ML library you use, so it shouldn't really make much of a difference between tensorflow and torch etc.
Name: {Learnable Boundary Guided Adversarial Training }
Authors: {Jiequan Cui, Shu Liu, Liwei Wang, Jiaya Jia}
Paper: {https://arxiv.org/abs/2011.11164}
Code: code
Venue: {venue if published}
Does the code implement the robust-ml API and include pre-trained models: {yes}
Dataset: {CIFAR-100}
Threat model: {threat model for which claims are made}
Natural accuracy: {60.55}
Claims: {30.20}