Beyond the model: Data pre-processing attack to deep learning models in Android apps

Ye Sang, Yujin Huang, Shuo Huang, Helei Cui

Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

1 Citation (Scopus)


The increasing popularity of deep learning (DL) models and the advantages of computing, including low latency and bandwidth savings on smartphones, have led to the emergence of intelligent mobile applications, also known as DL apps, in recent years. However, this technological development has also given rise to several security concerns, including adversarial examples, model stealing, and data poisoning issues. Existing works on attacks and countermeasures for on-device DL models have primarily focused on the models themselves. However, scant attention has been paid to the impact of data processing disturbance on the model inference. This knowledge disparity highlights the need for additional research to fully comprehend and address security issues related to data processing for on-device models. In this paper, we introduce a data processing-based attacks against real-world DL apps. In particular, our attack could influence the performance and latency of the model without affecting the operation of a DL app. To demonstrate the effectiveness of our attack, we carry out an empirical study on 517 real-world DL apps collected from Google Play. Among 320 apps utilizing MLkit, we find that 81.56% of them can be successfully attacked. The results emphasize the importance of DL app developers being aware of and taking actions to secure on-device models from the perspective of data processing.

Original languageEnglish
Title of host publicationProceedings of the Inaugural AsiaCCS 2023 Workshop on Secure and Trustworthy Deep Learning Systems, SecTL 2023
PublisherAssociation for Computing Machinery (ACM)
Number of pages9
ISBN (Electronic)9798400701818
Publication statusPublished - Jul 2023
EventWorkshop on Secure and Trustworthy Deep Learning Systems 2023 - Melbourne, Australia
Duration: 10 Jul 202310 Jul 2024 (Proceedings) (Website)


ConferenceWorkshop on Secure and Trustworthy Deep Learning Systems 2023
Abbreviated titleSecTL'23
Otherat AsiaCCS 2023
Internet address

Cite this