Threats to Training: A Survey of Poisoning Attacks and Defenses on Machine Learning Systems
ACM Computing Surveys · 31.07.2023 · 55 (7) · 1-36
DOI: 10.1145/3538707 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 15.12.2022. Verfasst von Zhibo Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 110-mal zitiert (Crossref) und nennt 96 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Key R&D Program of Zhejiang.
Abstract (Originalsprache)
Machine learning (ML) has been universally adopted for automated decisions in a variety of fields, including recognition and classification applications, recommendation systems, natural language processing, and so on. However, in light of high expenses on training data and computing resources, recent years have witnessed a rapid increase in outsourced ML training, either partially or completely, which provides vulnerabilities for adversaries to exploit. A prime threat in training phase is called poisoning attack, where adversaries strive to subvert the behavior of machine learning systems by poisoning training data or other means of interference. Although a growing number of relevant studies have been proposed, the research among poisoning attack is still overly scattered, with each paper focusing on a particular task in a specific domain. In this survey, we summarize and categorize existing attack methods and corresponding defenses, as well as demonstrate compelling application scenarios, thus providing a unified framework to analyze poisoning attacks. Besides, we also discuss the main limitations of current works, along with the corresponding future directions to facilitate further researches. Our ultimate motivation is to provide a comprehensive and self-contained survey of this growing field of research and lay the foundation for a more standardized approach to reproducible studies.
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- Key R&D Program of Zhejiang
Zitieren
APA
Wang, Z., Ma, J., Wang, X., Hu, J., Qin, Z., & Ren, K. (2023). Threats to Training: A Survey of Poisoning Attacks and Defenses on Machine Learning Systems. ACM Computing Surveys, 55(7), 1-36. https://doi.org/10.1145/3538707
Vancouver
Wang Z, Ma J, Wang X, Hu J, Qin Z, Ren K. Threats to Training: A Survey of Poisoning Attacks and Defenses on Machine Learning Systems. ACM Computing Surveys. 2023;55(7):1-36. doi:10.1145/3538707
BibTeX
@article{Wang2023,
author = {Wang, Zhibo and Ma, Jingjing and Wang, Xue and Hu, Jiahui and Qin, Zhan and Ren, Kui},
title = {Threats to Training: A Survey of Poisoning Attacks and Defenses on Machine Learning Systems},
journal = {ACM Computing Surveys},
year = {2023},
volume = {55},
number = {7},
pages = {1--36},
doi = {10.1145/3538707}
}
EUVIMED