{"ID":2873296,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.06371","arxiv_id":"2509.06371","title":"Breaking SafetyCore: Exploring the Risks of On-Device AI Deployment","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2509.06371","url_pdf":"https://arxiv.org/pdf/2509.06371v1","authors":"[\"Victor Guyomard\",\"Mathis Mauvisseau\",\"Marie Paindavoine\"]","published":"2025-09-08T06:53:13Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}