Files and links (1)
SubmittedOpen Access (License Unspecified), Open
Book chapter
Defenses Against Multi-sticker Physical Domain Attacks on Classifiers
Computer Vision – ECCV 2020 Workshops, pp 202-219
10 Jan 2021
Abstract
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
8 Record Views
5 citations in Scopus
Details
- Title
- Defenses Against Multi-sticker Physical Domain Attacks on Classifiers
- Creators
- Xinwei Zhao - Drexel UniversityMatthew C. Stamm - Drexel University
- Publication Details
- Computer Vision – ECCV 2020 Workshops, pp 202-219
- Series
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing; Cham
- Resource Type
- Book chapter
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Scopus ID
- 2-s2.0-85101422858
- Other Identifier
- 991019173675504721