no code implementations • 25 Nov 2022 • Muhammad Zaid Hameed, Beat Buesser
Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long.
no code implementations • ICML Workshop AML 2021 • Emre Ozfatura, Muhammad Zaid Hameed, Kerem Ozfatura, Deniz Gunduz
Hence, we propose a novel approach to identify the important features by employing counter-adversarial attacks, which highlights the consistency at the penultimate layer with respect to perturbations on input samples.
no code implementations • 14 Feb 2021 • Muhammad Zaid Hameed, Andras Gyorgy
Motivated by previous observations that the usually applied $L_p$ norms ($p=1, 2,\infty$) do not capture the perceptual quality of adversarial examples in image classification, we propose to replace these norms with the structural similarity index (SSIM) measure, which was developed originally to measure the perceptual similarity of images.
no code implementations • 27 Feb 2019 • Muhammad Zaid Hameed, Andras Gyorgy, Deniz Gunduz
We consider a communication scenario, in which an intruder tries to determine the modulation scheme of the intercepted signal.