An Intermediate-Level Attack Framework on the Basis of Linear Regression
This article substantially extends our work published at ECCV (Li et al., 2020), in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples. Specifically, we advocate a framework in which a direct linear mapping from the intermediate-level...
| Publié dans: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 3 vom: 04. März, Seite 2726-2735 |
|---|---|
| Auteur principal: | |
| Autres auteurs: | , , |
| Format: | Article en ligne |
| Langue: | English |
| Publié: |
2023
|
| Accès à la collection: | IEEE transactions on pattern analysis and machine intelligence |
| Sujets: | Journal Article |
| Résumé: | This article substantially extends our work published at ECCV (Li et al., 2020), in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples. Specifically, we advocate a framework in which a direct linear mapping from the intermediate-level discrepancies (between adversarial features and benign features) to prediction loss of the adversarial example is established. By delving deep into the core components of such a framework, we show that a variety of linear regression models can all be considered in order to establish the mapping, the magnitude of the finally obtained intermediate-level adversarial discrepancy is correlated with the transferability, and further boost of the performance can be achieved by performing multiple runs of the baseline attack with random initialization. In addition, by leveraging these findings, we achieve new state-of-the-arts on transfer-based l∞ and l2 attacks. Our code is publicly available at https://github.com/qizhangli/ila-plus-plus-lr |
|---|---|
| Description: | Date Completed 07.04.2023 Date Revised 07.04.2023 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
| ISSN: | 1939-3539 |
| DOI: | 10.1109/TPAMI.2022.3188044 |