Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors

Raz Lapid, Almog Dubin and Moshe Sipper ()
Additional contact information
Raz Lapid: Department of Computer Science, Ben-Gurion University, Beer-Sheva 8410501, Israel
Almog Dubin: DeepKeep, Tel-Aviv 6701203, Israel
Moshe Sipper: Department of Computer Science, Ben-Gurion University, Beer-Sheva 8410501, Israel

Mathematics, 2024, vol. 12, issue 22, 1-21

Abstract: Adaptive adversarial attacks, where adversaries tailor their strategies with full knowledge of defense mechanisms, pose significant challenges to the robustness of adversarial detectors. In this paper, we introduce RADAR (Robust Adversarial Detection via Adversarial Retraining), an approach designed to fortify adversarial detectors against such adaptive attacks while preserving the classifier’s accuracy. RADAR employs adversarial training by incorporating adversarial examples—crafted to deceive both the classifier and the detector—into the training process. This dual optimization enables the detector to learn and adapt to sophisticated attack scenarios. Comprehensive experiments on CIFAR-10, SVHN, and ImageNet datasets demonstrate that RADAR substantially enhances the detector’s ability to accurately identify adaptive adversarial attacks without degrading classifier performance.

Keywords: robustness; adversarial attacks; adaptive adversarial attacks; deep learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/22/3451/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/22/3451/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:22:p:3451-:d:1514350

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().