Beyond the Model: Data Pre-processing Attack to Deep Learning Models in Android Apps
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 55 references that are in the map. First posted on arXiv 6 May 2023.
Builds on
16 of 55 references.
References · 16
- 2016Adversarial examples in the physical worldcited by 1,769
- 2016Stealing Machine Learning Models via Prediction APIscited by 619
- 2020Entangled Watermarks as a Defense against Model Extractioncited by 149
- 2016Towards the Science of Security and Privacy in Machine Learningcited by 89
- 2018A First Look at Deep Learning Apps on Smartphonescited by 47
- 2021DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injectioncited by 44
- 2020Mind Your Weight(s): A Large-scale Study on Insufficient Machine Learning Model Protection in Mobile Appscited by 36
- 2023Training-free Lexical Backdoor Attacks on Language Modelscited by 31
- 2017Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developmentscited by 30
- 2021Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Appscited by 19
- 2020Comparison and Benchmarking of AI Models and Frameworks on Mobile Devicescited by 17
- 2018Deep Learning Towards Mobile Applicationscited by 16
4 more
- 2022Understanding Real-world Threats to Deep Learning Models in Android Appscited by 15
- 2021On Robustness of Neural Semantic Parserscited by 14
- 2022Smart App Attack: Hacking Deep Learning Models in Android Appscited by 12
- 2018A Large Scale Investigation of Obfuscation Use in Google Playcited by 1
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025Stealthy Backdoor Attack to Real-world Models in Android Apps
- 2024MalModel: Hiding Malicious Payload in Mobile Deep Learning Models with Black-box Backdoor Attack
- 2025THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models
- 2022Benchmarking of DL Libraries and Models on Mobile Devices
- 2021Robustness Analysis of Deep Learning Frameworks on Mobile Platforms
- 2024Deep Learning Model Security: Threats and Defenses
- 2025Data Poisoning in Deep Learning: A Survey
- 2022Publishing Efficient On-device Models Increases Adversarial Vulnerability