Add the EAD attack to torchattacks and bug fix

[rikonaka]

PR Type and Checklist

What kind of change does this PR introduce?

• [x] FIX BUG
  • [x] Fix bug in issues https://github.com/Harry24k/adversarial-attacks-pytorch/issues/136, call the _check_inputs and _check_outputs (also normalize) function in class Attack's __call__ function instead of every forward function (also remove all from forward function) in https://github.com/Harry24k/adversarial-attacks-pytorch/pull/137/commits/5fe65ec2fe01b8a57699d2cfb952d4dc02c2394f.
  • [x] DeepFool attack has one line bug in here, in fact, the value of label could be 9 but the length of value only 8 on CIFAR10, we don't need to get all non-label values from the jacobian matrix, fs-fs[label] will make the label row become 0, and set label row inf next then pick min value is not affect. I also modified deepfool's main loop to make the code lean and easy to read in https://github.com/Harry24k/adversarial-attacks-pytorch/pull/137/commits/9801db87f51ef225a0b8438132e7e044ac3481a5.
• [x] ADD ATTACK
  • [x] Add the EADL1 attack in https://github.com/Harry24k/adversarial-attacks-pytorch/pull/137/commits/51aafef265c8b7fe4ebfd6729b5bc1b549ae82ae.
  • [x] Add the EADEN (L1+L2) attack in https://github.com/Harry24k/adversarial-attacks-pytorch/pull/137/commits/51aafef265c8b7fe4ebfd6729b5bc1b549ae82ae.
• [x] Other... Please describe:
  • [x] Fix JSMA and SPSA parameters describe.
  • [x] Fix UPGD attack one_hot_labels error (same as previous CW bug).
  • [x] Some format change (use autopep8).
  • [x] Init normalization_used and _normalization_applied in __init__ function.
  • [x] Fix get_logits function how to check _normalization_applied.

[rikonaka]

On 64 CIFAR10 test datasets, the EADL1 untargeted attack accuracy drop to 1.56%, and the EADEN untargeted attack accuracy also drop to 1.56%.

I did not see any target attack method in paper...the value $t$ is not used in the Algorithm 1...but I still supported targeted attack in code, even though the accuracy rate would only drop to 64%. 🤨

[codecov-commenter]

Codecov Report

Merging #137 (c9e9531) into master (9a22433) will increase coverage by 1.83%. The diff coverage is 90.70%.

:exclamation: Current head c9e9531 differs from pull request most recent head 5fe65ec. Consider uploading reports for the commit 5fe65ec to get more accurate results

:mega: This organization is not using Codecov’s GitHub App Integration. We recommend you install it so Codecov can continue to function properly for your repositories. Learn more

@@            Coverage Diff             @@
##           master     #137      +/-   ##
==========================================
+ Coverage   71.25%   73.09%   +1.83%     
==========================================
  Files          41       43       +2     
  Lines        3500     3787     +287     
  Branches      500      535      +35     
==========================================
+ Hits         2494     2768     +274     
- Misses        852      857       +5     
- Partials      154      162       +8     

Impacted Files	Coverage Δ
torchattacks/attack.py	47.98% <16.00%> (+0.05%)	:arrow_up:
torchattacks/attacks/square.py	52.98% <33.33%> (ø)
torchattacks/attacks/pixle.py	58.12% <60.00%> (+0.91%)	:arrow_up:
torchattacks/attacks/upgd.py	62.82% <75.00%> (ø)
torchattacks/attacks/eaden.py	95.55% <95.55%> (ø)
torchattacks/attacks/eadl1.py	97.08% <97.08%> (ø)
torchattacks/__init__.py	100.00% <100.00%> (ø)
torchattacks/attacks/apgd.py	76.30% <100.00%> (ø)
torchattacks/attacks/apgdt.py	86.25% <100.00%> (ø)
torchattacks/attacks/autoattack.py	81.25% <100.00%> (ø)
... and 27 more

---

Continue to review full report in Codecov by Sentry.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 9a22433...5fe65ec. Read the comment docs.

[Harry24k]

I'm surprised that you were already fixed the normalization part 😄. The current validation check process has some issues when we use normalized_used=True, such as ValueError: Input must have a range [0, 1] (max: 1.0, min: -2.9802322387695312e-08). I'm working on it.

BTW, there is an error during the coverage check. Could you fix the problem? :

code_coverage/test_atks.py::test_atks_on_cifar10[OnePixel]
  /home/runner/work/adversarial-attacks-pytorch/adversarial-attacks-pytorch/torchattacks/attacks/_differential_evolution.py:592: RuntimeWarning: divide by zero encountered in double_scalars
    convergence=self.tol / convergence) is True):

[rikonaka]

Hi @Harry24k , I could not reproduce the same error that caused when I run OnePixel attack 😂.

It's looks like an error in the _differential_evolution.py file not OnePixel.

[Harry24k]

I cannot find the cause of the error, so I merge it and will update it!

[rikonaka]

Hi @Harry24k , I found the problem, in the line of _differential_evolution.py, the value of convergence could be 0 when run the OnePixel attack.

I modified the code so that the value is set to inf when it is divided by 0.