Journal
IEEE INTERNET OF THINGS JOURNAL
Volume 7, Issue 6, Pages 5103-5115Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2020.2975654
Keywords
Robot sensing systems; Perturbation methods; Neural networks; Surveillance; Taxonomy; Detectors; Adversarial attacks and defense; cyber-physical systems (CPSs); cyber-security
Categories
Funding
- GRF grant from the Research Grants Council of Hong Kong [CityU 11217817]
- Science Technology and Innovation Committee of Shenzhen Municipality [JCYJ20170818095109386]
Ask authors/readers for more resources
Cyber-security issues on adversarial attacks are actively studied in the field of computer vision with the camera as the main sensor source to obtain the input image or video data. However, in modern cyber-physical systems (CPSs), many other types of sensors are becoming popularly used, such as surveillance sensors, microphones, and textual interfaces. A series of recent works investigates the adversarial attacks and the potential defenses in these noncamera sensor-based CPSs. Therefore, this article provides a systematic discussion on these existing works and serves as a complimentary summary of the adversarial attacks and defenses for CPSs beyond the field of computer vision. We first introduce a general working flow for adversarial attacks on CPSs. On this basis, a clear taxonomy is provided to organize existing attacks effectively and indicate where the defenses can be potentially performed in CPSs as well. Then, we discuss these existing attacks and defenses with detailed comparison studies. Finally, we point out concrete research opportunities to be further explored along this research direction.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available