Logo image
Back
Defenses Against Multi-sticker Physical Domain Attacks on Classifiers
Book chapter   Open access   Peer reviewed

Defenses Against Multi-sticker Physical Domain Attacks on Classifiers

Xinwei Zhao and Matthew C. Stamm
Computer Vision – ECCV 2020 Workshops, pp 202-219
10 Jan 2021
DOI: https://doi.org/10.1007/978-3-030-66415-2_13
url
http://arxiv.org/abs/2101.11060View
Submitted Open Open Access (License Unspecified)

Abstract

Classifiers Deep learning Defenses Real-world adversarial attacks
Recently, physical domain adversarial attacks have drawn significant attention from the machine learning community. One important attack proposed by Eykholt et al. can fool a classifier by placing black and white stickers on an object such as a road sign. While this attack may pose a significant threat to visual classifiers, there are currently no defenses designed to protect against this attack. In this paper, we propose new defenses that can protect against multi-sticker attacks. We present defensive strategies capable of operating when the defender has full, partial, and no prior information about the attack. By conducting extensive experiments, we show that our proposed defenses can outperform existing defenses against physical attacks when presented with a multi-sticker attack.

Metrics

10 Record Views
5 citations in Scopus

Details

Logo image