New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Attack > Evasion > Momentum Iterative Method: major issues #2439
Comments
eliegoudout
changed the title
Attack > Evasion > BIM: Momentum issues
Attack > Evasion > Momentum Iterative Method: major issues
Apr 27, 2024
Quick notes for me when I'll fix it:
|
eliegoudout
added a commit
to eliegoudout/adversarial-robustness-toolbox-fix-FGM-L1
that referenced
this issue
May 7, 2024
Signed-off-by: Élie Goudout <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Stumbled upon 2 issues regarding the implementation of the momentum for Fast Gradient Method adversarial attack:
FGM
andPGD
: fix L1 and extend to Lp #2382 (comment));momentum
variable as a side effect, which doesn't always seem to work as expected (see [FIX + Enhancement]FGM
andPGD
: fix L1 and extend to Lp #2382 (comment)). As such, I believe that the current momentum iterative attack is actually only BIM!The first issue should be fixed by #2382, while the second should be independently investigated and fixed, as it may require some refactoring. Furthermore, it could be well-advised to add a test for a different decay value.
Edit: It looks like the tensorflow framework doesn't work with the in-place modification.
The text was updated successfully, but these errors were encountered: