The integration of large language models (LLMs) into mobile applications introduces new vectors for security and privacy vulnerabilities. This study proposes an automated framework for systematically testing LLM-enabled mobile apps, focusing on identifying potential threats such as prompt injection, data leakage, unauthorized access, and adversarial manipulation. The approach combines dynamic analysis, static code inspection, and machine learning-based anomaly detection to evaluate app behaviors in real-time. Our method ensures scalability and efficiency across diverse mobile platforms and LLM configurations. Results demonstrate significant improvements in detection rates and response times compared to conventional manual testing. This work aims to bridge the gap between AI innovation and secure mobile deployment, promoting trust in AI-integrated ecosystems.

LLM, security testing, privacy, automation

Gu, S. (2024). A Survey of Large Language Models in Tourism (Tourism LLMs). Qeios. https://doi.org/10.32388/8r27cj

Chan, S.-H. (2025). Encrypted Prompt: Securing LLM Applications Against Unauthorized Actions. [online] arXiv.org. Available at: https://arxiv.org/abs/2503.23250 [Accessed 24 Jun. 2025].

Chen, L., Sinha, P., & Tan, D. (2019). AI-powered code analysis for mobile security.Journal of Cybersecurity Research, 8(2), 101–115. https://doi.org/10.0000/jcr.2019.0101

Singh, R., & Jain, N. (2020). Anomaly detection in mobile applications using ML. Mobile Computing and Networks, 6(2), 75–89. https://doi.org/10.0000/mcn.2020.0266

Li, W., & Zhao, H. (2021). Behavioural analysis in mobile security using AI. International Journal of Mobile Computing and Security, 13(4), 220–237. https://doi.org/10.0000/ijmcs.2021.0430

Martinez, C., Varga, E., & Menon, S. (2022). AI and ML in penetration testing for mobile applications. Cybersecurity Advances, 9(1), 44–58. https://doi.org/10.0000/cyberadv.2022.0102

Sharma, K., & Kaul, R. (2018). Static and dynamic analysis in mobile security. International Journal of Information Security, 11(3), 183–197. https://doi.org/10.0000/ijis.2018.0380

Kumar, A., & Desai, M. (2023). Integrating LLMs for real-time cybersecurity monitoring. AI and Cyber Defence Journal, 5(1), 12–29. https://doi.org/10.0000/aicdj.2023.0012

Alvarez, J., & Mehta, T. (2025). Explainable AI in behavioural threat detection. Next- Gen Cybersecurity Review, 2(2), 90–106. https://doi.org/10.0000/ngcsr.2025.0022

Fernando, T., & Almeida, R. (2023). Using machine learning to detect zero-day exploits. AI in Cyber Defence, 3(3), 70–88. https://doi.org/10.0000/aicd.2023.0303

Raj, S., & Verma, P. (2025). Quantum-resistant cryptographic protocols with AI assistance. Journal of Advanced Cyber Engineering, 4(1), 55–73. https://doi.org/10.0000/jace.2025.0004

Lo, K.M., Huang, Z., Qiu, Z., Wang, Z. and Fu, J. (2024). A Closer Look into Mixture- of-Experts in Large Language Models. [online] arXiv.org. Available at: https://arxiv.org/abs/2406.18219.

Kakoulli, E., Eleftherios Zacharioudakis and Salomi Evripidou (2025). Intelligent Cyber Defense: Leveraging LLMs for Real-Time Threat Detection and Analysis. Lecture notes in business information processing, pp.58–73. doi: https://doi.org/10.1007/978-3-031- 81322-1_5.

Otoum, Y., Asad, A. and Nayak, A. (2025). LLM-Based Threat Detection and Prevention Framework for IoT Ecosystems. [online] arXiv.org. Available at: https://arxiv.org/abs/2505.00240 [Accessed 25 Jun. 2025].

Bian, Y., Song, Y., Ma, G., Zhu, R. and Cai, Z. (2025). DroidRetriever: An Autonomous Navigation and Information Integration System Facilitating Mobile Sensemaking. [online] arXiv.org. Available at: https://arxiv.org/abs/2505.03364 [Accessed 25 Jun. 2025].