Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.06371 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908524585418752 |
|---|---|
| author | Guyomard, Victor Mauvisseau, Mathis Paindavoine, Marie |
| author_facet | Guyomard, Victor Mauvisseau, Mathis Paindavoine, Marie |
| contents | Due to hardware and software improvements, an increasing number of AI models are deployed on-device. This shift enhances privacy and reduces latency, but also introduces security risks distinct from traditional software. In this article, we examine these risks through the real-world case study of SafetyCore, an Android system service incorporating sensitive image content detection. We demonstrate how the on-device AI model can be extracted and manipulated to bypass detection, effectively rendering the protection ineffective. Our analysis exposes vulnerabilities of on-device AI models and provides a practical demonstration of how adversaries can exploit them. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06371 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Breaking SafetyCore: Exploring the Risks of On-Device AI Deployment Guyomard, Victor Mauvisseau, Mathis Paindavoine, Marie Machine Learning Due to hardware and software improvements, an increasing number of AI models are deployed on-device. This shift enhances privacy and reduces latency, but also introduces security risks distinct from traditional software. In this article, we examine these risks through the real-world case study of SafetyCore, an Android system service incorporating sensitive image content detection. We demonstrate how the on-device AI model can be extracted and manipulated to bypass detection, effectively rendering the protection ineffective. Our analysis exposes vulnerabilities of on-device AI models and provides a practical demonstration of how adversaries can exploit them. |
| title | Breaking SafetyCore: Exploring the Risks of On-Device AI Deployment |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.06371 |