Assessing the Effectiveness of LLMs in Android Application Vulnerability Analysis

The increasing frequency of attacks on Android applications necessitates a comprehensive understanding of the capabilities of large language models (LLMs) in identifying potential vulnerabilities, which is key to mitigate the overall risk. To this end, the work at hand compares the ability of nine state-of-the-art LLMs to detect Android code vulnerabilities listed in the latest OWASP Mobile Top 10. Each LLM was evaluated against an open dataset of over 100 vulnerable code samples, including obfuscated ones, assessing each model’s ability to identify key vulnerabilities. Our analysis reveals the strengths and weaknesses of each LLM, identifying important factors that contribute to their performance. Additionally, we offer insights into context augmentation with retrievalaugmented generation (RAG) for detecting Android code vulnerabilities, which in turn may propel secure application development. Finally, while the reported findings regarding code vulnerability analysis show promise, they also reveal significant discrepancies among the different LLMs.

KOULIARIDIS Vasileios;  KAROPOULOS Georgios;  KAMBOURAKIS Georgios; 

2025-07-11

SPRINGER VERLAG

JRC137829

1611-3349 (online),   

https://publications.jrc.ec.europa.eu/repository/handle/JRC137829,   

10.1007/978-3-031-85593-1_9 (online),