HSJA
HSJA copied to clipboard
Jianbo-Lab
Could you explain the difference between the binary search in the initialize method [1] and the binary search right after it [2]? It seems to me that the second one...
Dear Sir: In your code `def approximate_gradient(model, sample, num_evals, delta, params)`, https://github.com/Jianbo-Lab/HSJA/blob/daecd5c7055d5214b39c34a7a28a98acd3557fbc/hsja.py#L165 I thought this code is used for estimating the true gradient as the following code: ``` def get_grad(self,...
Hi, Thank you for providing the source code of the attack. However, this code attacks only for the CIFAR10 resnet model. Is there any pretrained model that you used for...
The default parameters does not work well for Inception v3 model on ImageNet dataset in my setup. This repo does not provide ImageNet models and corresponding parameters for HSJA. Can...
Hello,I've met a problem. when I use MNIST or CIFAR10 or ImageNet ,the l2 norm almost unchanged after the first binary search. looking forward to your reply ，thanks
The code starts from https://github.com/Jianbo-Lab/HSJA/blob/master/hsja.py#L182 What does these codes mean? I can understand the above code to estimate gradients, which is mainly RGF method.
The pseudocode in the paper describes that under a certain delta value, when the output results of the classifier are all zero, the delta value will be reduced by half,...
