LDMDroid: Leveraging LLMs for Detecting Data Manipulation Errors in Android Apps
This addresses reliability issues for Android app developers by automating error detection, though it is incremental as it builds on existing UI testing methods with LLM enhancements.
The paper tackled the problem of detecting data manipulation errors in Android apps by proposing LDMDroid, an automated UI testing framework that uses large language models to generate event sequences and visual features for verification, resulting in improved triggering success rates and the discovery of 17 unique bugs with 14 confirmed and 11 fixed.
Android apps rely heavily on Data Manipulation Functionalities (DMFs) for handling app-specific data through CRUDS operations, making their correctness vital for reliability. However, detecting Data Manipulation Errors (DMEs) is challenging due to their dependence on specific UI interaction sequences and manifestation as logic bugs. Existing automated UI testing tools face two primary challenges: insufficient UI path coverage for adequate DMF triggering and reliance on manually written test scripts. To address these issues, we propose an automated approach using Large Language Models (LLMs) for DME detection. We developed LDMDroid, an automated UI testing framework for Android apps. LDMDroid enhances DMF triggering success by guiding LLMs through a state-aware process for generating UI event sequences. It also uses visual features to identify changes in data states, improving DME verification accuracy. We evaluated LDMDroid on 24 real-world Android apps, demonstrating improved DMF triggering success rates compared to baselines. LDMDroid discovered 17 unique bugs, with 14 confirmed by developers and 11 fixed. The tool is publicly available at https://github.com/runnnnnner200/LDMDroid.