Logo image
Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks
Journal article   Open access   Peer reviewed

Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks

Husheng Han, Xing Hu, Yifan Hao, Kaidi Xu, Pucheng Dang, Ying Wang, Yongwei Zhao, Zidong Du, Qi Guo, Yanzhi Wang, …
IEEE transactions on computer-aided design of integrated circuits and systems, v 43(1), pp 366-379
01 Jan 2024
url
https://arxiv.org/abs/2208.09195View

Abstract

Computer Science, Hardware & Architecture Computer Science, Interdisciplinary Applications Engineering, Electrical & Electronic Science & Technology Computer Science Engineering Technology
DNN-based video object detection (VOD) powers autonomous driving and video surveillance industries with rising importance and promising opportunities. However, adversarial patch attack yields huge concern in live vision tasks because of its practicality, feasibility, and powerful attack effectiveness. This work proposes Themis, a software/hardware system to defend against adversarial patches for real-time robust VOD. We observe that adversarial patches exhibit extremely localized superficial feature importance in a small region with nonrobust predictions, and thus propose the adversarial region detection algorithm for adversarial effect elimination. Themis also proposes a systematic design to efficiently support the algorithm by eliminating redundant computations and memory traffics. Experimental results show that the proposed methodology can effectively recover the system from the adversarial attack with negligible hardware overhead.

Metrics

15 Record Views
3 citations in Scopus

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#3 Good Health and Well-Being

Source: SDGs in the Output

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
International collaboration
Web of Science research areas
Computer Science, Hardware & Architecture
Computer Science, Interdisciplinary Applications
Engineering, Electrical & Electronic
Logo image