GSE: Group-wise Sparse and Explainable Adversarial Attacks

Sparse adversarial attacks fool deep neural networks (DNNs) through minimal pixel perturbations, often regularized by the ℓ0 norm. Recent efforts have replaced this norm with a structural sparsity regularizer, such as the nuclear group norm, to craft group-wise sparse adversarial attacks.

Data and Resources

Cite this as

Shpresim Sadiku, Moritz Wagner, Sebastian Pokutta (2024). Dataset: GSE: Group-wise Sparse and Explainable Adversarial Attacks. https://doi.org/10.57702/2zn1i7s2

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2311.17434
Author Shpresim Sadiku
More Authors
Moritz Wagner
Sebastian Pokutta
Homepage https://github.com/wagnermoritz/GSE