convex_adversarial
convex_adversarial copied to clipboard
locuslab
A method for training neural networks that are provably robust to adversarial attacks.
Wondering if anyone has built (or has plans to) build support for nn.MaxPool2d?
Hi, I've run the code like the following for epsilon=8/255=0.03137 on CIFAR-10: `python examples/cifar.py --proj 50 --norm_train l1_median --norm_test l1 --starting_epsilon 0.001 --epsilon 0.03137 --schedule_length 20 --epochs 60 --cuda_ids 1`...
Hi, I've run mnist.py on a single Titan X (Pascal) with the default settings. However, the speed is much slower(x3) than that reported in the literature (Table 1). [Scaling provable...
Many of the proofs assume that the label `y` is an one-hot vector. However, in situations such as Virtual Adversarial Training, we would like to find a perturbation that maximizes...
The same code works with the same value of `epsilon` when it is changed to a Python built-in `float` instead. Tested with PyTorch 0.4.0 (CPU).
After changing the padding of conv2d to zero, error occurred below： File "fashion_mnist.py", line 59, in args.alpha_grad, args.scatter_grad, l1_proj=args.l1_proj) File "/home/songcb/convex_adversarial-master/examples/trainer.py", line 22, in train_robust scatter_grad=scatter_grad) File "/home/songcb/.local/lib/python3.6/site-packages/convex_adversarial-0.2-py3.6.egg/convex_adversarial/dual.py", line 182,...
Dear LocusLab members, how difficult would it to add support for network shapes that are not a simple chaint? There are a few applications in which they make sense (at...
I am trying to understand the original code as understanding original paper seems simpler. While trying to optimize Robust Neural Network in 2D.ipynb I get error as: ``` IndexError Traceback...
