Journal article
Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks
IEEE transactions on computer-aided design of integrated circuits and systems, v 43(1), pp 366-379
01 Jan 2024
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
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
Details
- Title
- Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks
- Creators
- Husheng Han - Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100190, Peoples R ChinaXing Hu - Institute of Computing TechnologyYifan Hao - Institute of Computing TechnologyKaidi Xu - Drexel University, Computer SciencePucheng Dang - Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100190, Peoples R ChinaYing Wang - Northeastern Univ, Dept Elect & Comp Engn, Boston, MA 02115 USAYongwei Zhao - Institute of Computing TechnologyZidong Du - Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100190, Peoples R ChinaQi Guo - Institute of Computing TechnologyYanzhi Wang - Northeastern UniversityXishan Zhang - Institute of Computing TechnologyTianshi Chen - Institute of Computing Technology
- Publication Details
- IEEE transactions on computer-aided design of integrated circuits and systems, v 43(1), pp 366-379
- Publisher
- IEEE
- Number of pages
- 14
- Grant note
- National Key Research and Development Program of China
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:001129816700018
- Scopus ID
- 2-s2.0-85168294164
- Other Identifier
- 991021861187804721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
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