Towards Stealing Deep Neural Networks on Mobile Devices
Document Type
Book Chapter
Publication Date
11-4-2021
Department
Department of Computer Science
Abstract
Recently, deep neural networks (DNN) are increasingly deployed on mobile computing devices. Compared to the traditional cloud-based DNN services, the on-device DNN provides immediate responses without relying on network availability or bandwidth and can boost security and privacy by preventing users’ data from transferring over the untrusted communication channels or cloud servers. However, deploying DNN models on the mobile devices introduces new attack vectors on the models. Previous studies have shown that the DNN models are prone to model stealing attacks in the cloud setting, by which the attackers can steal the DNN models accurately. In this work, for the first time, we study the model stealing attacks on the deep neural networks running in the mobile devices, by interacting with mobile applications. Our experimental results on various datasets confirm the feasibility of stealing DNN models in mobile devices with high accuracy and small overhead.
Publication Title
Security and Privacy in Communication Networks
Recommended Citation
Danda, S.,
Yuan, X.,
&
Chen, B.
(2021).
Towards Stealing Deep Neural Networks on Mobile Devices.
Security and Privacy in Communication Networks, 495-508.
http://doi.org/10.1007/978-3-030-90022-9_27
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/15651
Publisher's Statement
© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2021. Publisher’s version of record: https://doi.org/10.1007/978-3-030-90022-9_27