Machine Learning Models Have a Supply Chain Problem
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912400713711616 |
|---|---|
| author | Meiklejohn, Sarah Blauzvern, Hayden Maruseac, Mihai Schrock, Spencer Simon, Laurent Shumailov, Ilia |
| author_facet | Meiklejohn, Sarah Blauzvern, Hayden Maruseac, Mihai Schrock, Spencer Simon, Laurent Shumailov, Ilia |
| contents | Powerful machine learning (ML) models are now readily available online, which creates exciting possibilities for users who lack the deep technical expertise or substantial computing resources needed to develop them. On the other hand, this type of open ecosystem comes with many risks. In this paper, we argue that the current ecosystem for open ML models contains significant supply-chain risks, some of which have been exploited already in real attacks. These include an attacker replacing a model with something malicious (e.g., malware), or a model being trained using a vulnerable version of a framework or on restricted or poisoned data. We then explore how Sigstore, a solution designed to bring transparency to open-source software supply chains, can be used to bring transparency to open ML models, in terms of enabling model publishers to sign their models and prove properties about the datasets they use. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22778 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Machine Learning Models Have a Supply Chain Problem Meiklejohn, Sarah Blauzvern, Hayden Maruseac, Mihai Schrock, Spencer Simon, Laurent Shumailov, Ilia Machine Learning Cryptography and Security Powerful machine learning (ML) models are now readily available online, which creates exciting possibilities for users who lack the deep technical expertise or substantial computing resources needed to develop them. On the other hand, this type of open ecosystem comes with many risks. In this paper, we argue that the current ecosystem for open ML models contains significant supply-chain risks, some of which have been exploited already in real attacks. These include an attacker replacing a model with something malicious (e.g., malware), or a model being trained using a vulnerable version of a framework or on restricted or poisoned data. We then explore how Sigstore, a solution designed to bring transparency to open-source software supply chains, can be used to bring transparency to open ML models, in terms of enabling model publishers to sign their models and prove properties about the datasets they use. |
| title | Machine Learning Models Have a Supply Chain Problem |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2505.22778 |