Metraipolis › archive › dc_696f0f6fbed4

arXiv 2610.12893: Vulnerable Models in the AI Supply Chain: An Empirical Study of Adoption, Propagation, and Usage Patterns

Source
Metraipolis archive
Original
https://arxiv.org/abs/2610.12893
License (as archived)
CC-BY-4.0
Archived
2026-10-13T10:42:45.234Z
SHA-256 of the archived text
27c1478d625a0d1cecd14ea0ca178bd038d316c221c64cdffe2c1581a288eeb4
Stable URL of this page
https://metraipolis.com/documento/dc_696f0f6fbed4

How to cite

arXiv 2610.12893: Vulnerable Models in the AI Supply Chain: An Empirical Study of Adoption, Propagation, and Usage Patterns — Metraipolis archive, https://arxiv.org/abs/2610.12893 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_696f0f6fbed4 (Metraipolis archive dc_696f0f6fbed4, sha256 27c1478d625a0d1cecd14ea0ca178bd038d316c221c64cdffe2c1581a288eeb4)
BibTeX
@misc{dc696f0f6fbed4,
  title = {arXiv 2610.12893: Vulnerable Models in the AI Supply Chain: An Empirical Study of Adoption, Propagation, and Usage Patterns},
  howpublished = {Metraipolis archive},
  url = {https://arxiv.org/abs/2610.12893},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_696f0f6fbed4; sha256 27c1478d625a0d1cecd14ea0ca178bd038d316c221c64cdffe2c1581a288eeb4},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.12893. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The rapid integration of Artificial Intelligence (AI) models has established a complex supply chain, but many of these shared artifacts harbor severe vulnerabilities such as insecure serialization and architectural backdoors. While prior efforts have extensively scanned model registries to flag malicious artifacts, a critical gap remains in understanding how developers actually adopt and integrate these unsafe models into downstream software systems. We bridge this gap by conducting a large-scale empirical study on the usage and propagation of 16,977 known vulnerable models on HuggingFace flagged by InsightDB. We track their prevalence across GitHub repositories, software packages, fine-tuning chains, and deployed applications. Our analysis reveals that, despite being publicly flagged, these vulnerable models appear in over 21,000 code locations across more than 5,000 open-source repositories, with 3,757 distinct flagged models (22.1\%) actively referenced in at least one project. To understand how these models are integrated in code and identify recurring usage patterns, we categorize and analyze the recurring patterns surrounding them via a customized pipeline that combines Code Property Graphs extraction with a tailored Frequent Subgraph Mining approach. Across all patterns, we find no evidence of provenance verification or model sanitization logic, with developers frequently bypassing security parameters or delegating trust to permissive framework defaults. These findings underscore that scanning model files alone is insufficient, highlighting the urgent need for context-aware security analysis and stricter integration guardrails at the application layer of the AI supply chain.

Articolo: «Vulnerable Models in the AI Supply Chain: An Empirical Study of Adoption, Propagation, and Usage Patterns» — Nguyen, The Anh; Le, Triet Huynh Minh; Babar, M. Ali (2026-10-09), arXiv:2610.12893, categoria cs.CR (sicurezza e crittografia).
Fonte: https://arxiv.org/abs/2610.12893
Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv.
Consultato il 2026-10-13T10:42:37Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.