Towards Stealing Deep Neural Networks on Mobile Devices
Document Type
Conference Proceeding
Publication Date
1-1-2021
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
Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
ISBN
9783030900212
Recommended Citation
Danda, S.,
Yuan, X.,
&
Chen, B.
(2021).
Towards Stealing Deep Neural Networks on Mobile Devices.
Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST,
399 LNICST, 495-508.
http://doi.org/10.1007/978-3-030-90022-9_27
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/15626