Does this work on L-2 norm based attacks?

xuanqing94 / BayesianDefense

Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network

MIT License

61 stars 12 forks source link

Does this work on L-2 norm based attacks? #4

Open RaymondGsc opened 5 years ago

xuanqing94 commented 5 years ago

I didn't test L2 norm attacks, but I think the results should be the same. The only change we need to make is to replace linf_sgd.py in /attacker directory with the standard SGD in pytorch.