-
I am not sure if the code for MI-FGSM is correct, since the gradient is expected to be calculated in each iteration rather than a single value for all iterations?
-
Some attacks implemented in torchattacks have better results when used in combinations with other attacks, as reported in their papers.
For example, [the paper proposing DI2-FGSM](https://arxiv.or…
-
Hello, I am currently reproducing your paper. Regarding Figure 4, I have some questions that I would like to ask you:
1. Is the dataset Imagene-compatible?
2. Besides DiffAttack, which specific surr…
-
-
I found that when running the MI-FGSM code, the final accuracy is independent of the decay_factor parameter, which leads to the results of MI-FGSM and I-FGSM always being the same. How can this issue…
-
感谢您完善的实验和详实的方法阐述！
最近我们也在进行有对抗样本方向的工作 ，我们想引用您的文章以及部分实验数据（Table.2 Dodging）与我们的方法在同条件下进行对比（_我们在Arcface SEResNet50 IR 做到了61，根据经验应该是没有你们的工作更强了_👍）
不知道您是否方便联系一下QQ？我们在本地跑的过程中遇到了一些权重文件缺失的问题(如：tiattack.py…
-
### ✨ Short description of the bug [tl;dr]
whether use eps-ball for MI-FGSM
### 💬 Detailed code and results
I just double checked with the pseudo code of the MI-FGSM and other implementaion, it see…
-
在运行RDCN+TK.py代码时，看到Likelihood maximization更新x时使用的似乎是L2_clamp，与paper中的似乎不同，参数设置也不太一样。不知您是否方便在readme中给出比较详细的解释，谢谢
-
Thanks for your excellent work. 😃
We wonder the concrete FSGM parameters used in your paper, since we did not find any code for them in this repo.
Conventionally, the FSGM parameters are attack …
-
I observed that the weight in timm of Incv4 and IncResV2 is different from tensorflow. So do you have pytorch weight of Incv4 and IncResV2(Same weight with MI-FGSM, TI-FGSM...etc), could you please sh…