Breaking SafetyCore: Exploring the Risks of On-Device AI Deployment
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 15 references that are in the map. First posted on arXiv 8 Sep 2025.
Builds on
8 of 15 references.
References · 8
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2016The Mythos of Model Interpretabilitycited by 721
- 2021A White Paper on Neural Network Quantizationcited by 472
- 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 434
- 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 66
- 2024Investigating White-Box Attacks for On-Device Modelscited by 6
Built on by
Not cited yet.