Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance
ACM Computing Surveys · 30.06.2025 · 57 (6) · 1-42
DOI: 10.1145/3645102 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 10.02.2025. Verfasst von Wenqi Wei und 1 weiteren Autor:innen. Die Arbeit wurde bisher 70-mal zitiert (Crossref) und nennt 242 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF CISE.
Abstract (Originalsprache)
Emerging Distributed AI systems are revolutionizing big data computing and data processing capabilities with growing economic and societal impact. However, recent studies have identified new attack surfaces and risks caused by security, privacy, and fairness issues in AI systems. In this article, we review representative techniques, algorithms, and theoretical foundations for trustworthy distributed AI through robustness guarantee, privacy protection, and fairness awareness in distributed learning. We first provide a brief overview of alternative architectures for distributed learning, discuss inherent vulnerabilities for security, privacy, and fairness of AI algorithms in distributed learning, and analyze why these problems are present in distributed learning regardless of specific architectures. Then, we provide a unique taxonomy of countermeasures for trustworthy distributed AI, covering (1) robustness to evasion attacks and irregular queries at inference, and robustness to poisoning attacks, Byzantine attacks, and irregular data distribution during training; (2) privacy protection during distributed learning and model inference at deployment; and (3) AI fairness and governance with respect to both data and models. We conclude with a discussion on open challenges and future research directions toward trustworthy distributed AI, such as the need for trustworthy AI policy guidelines, the AI responsibility-utility co-design, and incentives and compliance.
Förderung
- NSF CISE
Zitieren
APA
Wei, W., & Liu, L. (2025). Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance. ACM Computing Surveys, 57(6), 1-42. https://doi.org/10.1145/3645102
Vancouver
Wei W, Liu L. Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance. ACM Computing Surveys. 2025;57(6):1-42. doi:10.1145/3645102
BibTeX
@article{Wei2025,
author = {Wei, Wenqi and Liu, Ling},
title = {Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {6},
pages = {1--42},
doi = {10.1145/3645102}
}
EUVIMED