There is a newer version of the record available.

Published February 8, 2025 | Version v0.2.3
Software Open

Adversarial Library

Authors/Creators

  • 1. ÉTS Montréal

Description

  • Add properly parallelized DeepFool attack with sample-wise early-stopping
  • Add SuperDeepFool attack
  • Improve other label generation used in FAB and DF
  • Fix pyproject.toml to correctly discover modules

Notes

If you use this software, please cite it using the metadata from this file.

Files

jeromerony/adversarial-library-v0.2.3.zip

Files (93.8 kB)

Name Size Download all
md5:70ffd959b1813b3effecdbd60e9267c1
93.8 kB Preview Download

Additional details

Related works

Is supplement to
Software: https://github.com/jeromerony/adversarial-library/tree/v0.2.3 (URL)

Software

Repository URL
https://github.com/jeromerony/adversarial-library