A Self-supervised Approach for Adversarial Robustness

Muzammal Naseer, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Fatih Porikli

Research output: Contribution to journalConference articlepeer-review

23 Citations (Scopus)

Abstract

Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock towards their real-world deployment. Transferability of adversarial examples demand generalizable defenses that can provide cross-task protection. Adversarial training that enhances robustness by modifying target model's parameters lacks such generalizability. On the other hand, different input processing based defenses fall short in the face of continuously evolving attacks. In this paper, we take the first step to combine the benefits of both approaches and propose a self-supervised adversarial training mechanism in the input space. By design, our defense is a generalizable approach and provides significant robustness against the\textbf{unseen} adversarial attacks (\eg by reducing the success rate of translation-invariant\textbf{ensemble} attack from 82.6\% to 31.9\% in comparison to previous state-of-the-art). It can be deployed as a plug-and-play solution to protect a variety of vision systems, as we demonstrate for the case of classification, segmentation and detection.

Original languageEnglish
Article number9156294
Pages (from-to)259-268
Number of pages10
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
Publication statusPublished - 2020
Externally publishedYes
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States
Duration: 14 Jun 202019 Jun 2020

Fingerprint

Dive into the research topics of 'A Self-supervised Approach for Adversarial Robustness'. Together they form a unique fingerprint.

Cite this