English

Evaluating Model Robustness Using Adaptive Sparse L0 Regularization

Machine Learning 2024-08-29 v1 Artificial Intelligence

Abstract

Deep Neural Networks have demonstrated remarkable success in various domains but remain susceptible to adversarial examples, which are slightly altered inputs designed to induce misclassification. While adversarial attacks typically optimize under Lp norm constraints, attacks based on the L0 norm, prioritising input sparsity, are less studied due to their complex and non convex nature. These sparse adversarial examples challenge existing defenses by altering a minimal subset of features, potentially uncovering more subtle DNN weaknesses. However, the current L0 norm attack methodologies face a trade off between accuracy and efficiency either precise but computationally intense or expedient but imprecise. This paper proposes a novel, scalable, and effective approach to generate adversarial examples based on the L0 norm, aimed at refining the robustness evaluation of DNNs against such perturbations.

Keywords

Cite

@article{arxiv.2408.15702,
  title  = {Evaluating Model Robustness Using Adaptive Sparse L0 Regularization},
  author = {Weiyou Liu and Zhenyang Li and Weitong Chen},
  journal= {arXiv preprint arXiv:2408.15702},
  year   = {2024}
}

Comments

Accepted by the 20th International Conference on Advanced Data Mining and Applications (ADMA 2024)