SoK: Colluding Adversaries in Machine Learning Pipelines

Computer Science > Cryptography and Security [Submitted on 8 Jun 2026] SoK: Colluding Adversaries in Machine Learning Pipelines Vasisht Duddu, Lipeng He, Asim Waheed, N. Asokan Machine learning (ML) models are susceptible to various security, privacy, and fairness risks. Adversaries with different characteristics (i.e., objectives, knowledge, and capabilities) can collude by executing one attack to amplify others. Existing work lacks a systematic framework to explore collusion among adversaries, and to study the implications of the adversaries' characteristics. We present a framework covering collusion (a) between train- and inference-time adversaries, and (b) among inference-time adversaries. Our framework accounts for factors enabling collusion between adversaries. We propose a guideline to conjecture about the potential for collusion using enabling factors. We use it to explain prior work, conjecture about unexplored collusions, and empirically validate five such cases. Finally, we discuss how adversaries' characteristics influence the potential for collusion. Comments: USENIX Security Symposium, 2026 Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2606.10091 [cs.CR]   (or arXiv:2606.10091v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.10091 Focus to learn more Submission history From: Vasisht Duddu [view email] [v1] Mon, 8 Jun 2026 19:16:58 UTC (72 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)