Evaluating Model Robustness Using Adaptive Sparse L0 Regularization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916373290024960 |
|---|---|
| author | Liu, Weiyou Li, Zhenyang Chen, Weitong |
| author_facet | Liu, Weiyou Li, Zhenyang Chen, Weitong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_15702 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evaluating Model Robustness Using Adaptive Sparse L0 Regularization Liu, Weiyou Li, Zhenyang Chen, Weitong Machine Learning Artificial Intelligence F.2.2, I.2.7 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. |
| title | Evaluating Model Robustness Using Adaptive Sparse L0 Regularization |
| topic | Machine Learning Artificial Intelligence F.2.2, I.2.7 |
| url | https://arxiv.org/abs/2408.15702 |