Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps

01/12/2021
by   Yujin Huang, et al.
0

Deep learning has shown its power in many applications, including object detection in images, natural-language understanding, and speech recognition. To make it more accessible to end users, many deep learning models are now embedded in mobile apps. Compared to offloading deep learning from smartphones to the cloud, performing machine learning on-device can help improve latency, connectivity, and power consumption. However, most deep learning models within Android apps can easily be obtained via mature reverse engineering, while the models' exposure may invite adversarial attacks. In this study, we propose a simple but effective approach to hacking deep learning models using adversarial attacks by identifying highly similar pre-trained models from TensorFlow Hub. All 10 real-world Android apps in the experiment are successfully attacked by our approach. Apart from the feasibility of the model attack, we also carry out an empirical study that investigates the characteristics of deep learning models used by hundreds of Android apps on Google Play. The results show that many of them are similar to each other and widely use fine-tuning techniques to pre-trained models on the Internet.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

07/27/2021

Towards Black-box Attacks on Deep Learning Apps

Deep learning is a powerful weapon to boost application performance in m...
11/08/2018

A First Look at Deep Learning Apps on Smartphones

We are in the dawn of deep learning explosion for smartphones. To bridge...
01/18/2021

DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection

Deep learning models are increasingly used in mobile applications as cri...
07/14/2017

Towards Efficient Deep Inference for Mobile Applications

Mobile applications are benefiting significantly from the advancement in...
07/14/2017

Cloud-based or On-device: An Empirical Study of Mobile Deep Inference

Modern mobile applications are benefiting significantly from the advance...
01/08/2019

Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Apps

Deep learning solutions are being increasingly used in mobile applicatio...
08/01/2018

Tackling Android Stego Apps in the Wild

Digital image forensics is a young but maturing field, encompassing key ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.