LDMDroid: Leveraging LLMs for Detecting Data Manipulation Errors in Android Apps

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xiao, Xiangyang, Huang, Huaxun, Wu, Rongxin
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909029121392640
author Xiao, Xiangyang
Huang, Huaxun
Wu, Rongxin
author_facet Xiao, Xiangyang
Huang, Huaxun
Wu, Rongxin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00458
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LDMDroid: Leveraging LLMs for Detecting Data Manipulation Errors in Android Apps
Xiao, Xiangyang
Huang, Huaxun
Wu, Rongxin
Software Engineering
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.
title LDMDroid: Leveraging LLMs for Detecting Data Manipulation Errors in Android Apps
topic Software Engineering
url https://arxiv.org/abs/2604.00458