# Automation Slicing and Testing for in-App Deep Learning Models

arXiv: https://arxiv.org/abs/2205.07228 · HTML: https://mlsanity.com/paper/2205.07228/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2022.

## Built on by (most cited first, 1 of 1)

- [IMAGINE: An Integrated Model of Artificial Intelligence-Mediated Communication Effects](https://mlsanity.com/paper/2212.08658/) (2022)

## Abstract (arXiv)

Intelligent Apps (iApps), equipped with in-App deep learning (DL) models, are emerging to offer stable DL inference services. However, App marketplaces have trouble auto testing iApps because the in-App model is black-box and couples with ordinary codes. In this work, we propose an automated tool, ASTM, which can enable large-scale testing of in-App models. ASTM takes as input an iApps, and the outputs can replace the in-App model as the test object. ASTM proposes two reconstruction techniques to translate the in-App model to a backpropagation-enabled version and reconstruct the IO processing code for DL inference. With the ASTM's help, we perform a large-scale study on the robustness of 100 unique commercial in-App models and find that 56% of in-App models are vulnerable to robustness issues in our context. ASTM also detects physical attacks against three representative iApps that may cause economic losses and security issues.