A First Look at On-device Models in iOS Apps

TL;DR

This paper presents the first empirical analysis of on-device deep learning models in iOS apps, revealing their structure, usage, and security vulnerabilities, and proposing new attack methods to exploit these vulnerabilities.

Contribution

It provides the first detailed study of on-device models in iOS apps, including their frameworks, structures, and security issues, along with novel attack strategies.

Findings

On-device models are widely adopted in iOS apps.

Proposed attack methods effectively exploit vulnerabilities.

Real-world iOS apps are vulnerable to these attacks.

Abstract

Powered by the rising popularity of deep learning techniques on smartphones, on-device deep learning models are being used in vital fields like finance, social media, and driving assistance. Because of the transparency of the Android platform and the on-device models inside, on-device models on Android smartphones have been proven to be extremely vulnerable. However, due to the challenge in accessing and analysing iOS app files, despite iOS being a mobile platform as popular as Android, there are no relevant works on on-device models in iOS apps. Since the functionalities of the same app on Android and iOS platforms are similar, the same vulnerabilities may exist on both platforms. In this paper, we present the first empirical study about on-device models in iOS apps, including their adoption of deep learning frameworks, structure, functionality, and potential security issues. We study why current developers use different on-device models for one app between iOS and Android. We propose a more general attack against white-box models that does not rely on pre-trained models and a new adversarial attack approach based on our findings to target iOS's gray-box on-device models. Our results show the effectiveness of our approaches. Finally, we successfully exploit the vulnerabilities of on-device models to attack real-world iOS apps.