xiaosen-wang

Please add our CVPR 2021 paper

1

Please add our CVPR 2021 paper in adversarial example: Enhancing the Transferability of Adversarial Attacks through Variance Tuning paper link: https://arxiv.org/abs/2103.15571 code link: https://github.com/JHL-HUST/VT Thanks very much!

Please add our ICCV 2021 paper in adversarial example: Admix: Enhancing the Transferability of Adversarial Attacks paper link: https://arxiv.org/abs/2102.00436 code link: https://github.com/JHL-HUST/Admix Thanks very much!

03_linreg_starter will be overwrite loss

1

_, loss = ########## TO DO ############ total_loss += loss Here the loss variable name will overwrite the loss function so that in next epoch there will be a error...

When I run fgsm to attack the model with defense-GAN, I found that defense-GAN indeed defend the attack. However, the distortion between benign images and adversarial images is zero, which...

I try to use the code to attack models implemented in Keras. There is no problem when using fgsm. However, when I use deepfool, I get an error: Traceback (most...