Search Results for author: Muhammad Zaid Hameed

Found 4 papers, 0 papers with code

Boundary Adversarial Examples Against Adversarial Overfitting

no code implementations25 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.

Memorization

Less is More: Feature Selection for Adversarial Robustness with Compressive Counter-Adversarial Attacks

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.

Adversarial Robustness feature selection

Perceptually Constrained Adversarial Attacks

no code implementations14 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.

Image Classification SSIM

The Best Defense Is a Good Offense: Adversarial Attacks to Avoid Modulation Detection

no code implementations27 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.

Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.