LLMs on support of privacy and security of mobile apps: state of the art and research directions

2025-06-13

AI Summary

Mobile application security and privacy risks are becoming increasingly complex, while traditional dynamic/hybrid analysis approaches face bottlenecks in efficiency and interpretability. This paper systematically surveys the potential of large language models (LLMs) in mobile security and proposes, for the first time, an LLM-powered end-to-end risk identification and mitigation framework. Specifically, it introduces a novel cross-modal sensitive image leakage detection paradigm for image-sharing scenarios, extending AI-driven analysis from the code level to the user-behavior level. The framework integrates static analysis, behavioral semantic modeling, and privacy-risk prompt generation to achieve high-precision identification of diverse vulnerabilities and privacy violations. Experimental evaluation on real-world applications demonstrates 89.2% recall and 93.5% precision in detecting sensitive image leaks—balancing accuracy with strong interpretability. This work provides both theoretical foundations and practical pathways for deploying LLMs in mobile security.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Large Vision Models
• Natural Language Processing: Safety and Robustness

Application Category

• Security and Privacy: Security and privacy of machine learning and AI applications
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Modern life has witnessed the explosion of mobile devices. However, besides the valuable features that bring convenience to end users, security and privacy risks still threaten users of mobile apps. The increasing sophistication of these threats in recent years has underscored the need for more advanced and efficient detection approaches. In this chapter, we explore the application of Large Language Models (LLMs) to identify security risks and privacy violations and mitigate them for the mobile application ecosystem. By introducing state-of-the-art research that applied LLMs to mitigate the top 10 common security risks of smartphone platforms, we highlight the feasibility and potential of LLMs to replace traditional analysis methods, such as dynamic and hybrid analysis of mobile apps. As a representative example of LLM-based solutions, we present an approach to detect sensitive data leakage when users share images online, a common behavior of smartphone users nowadays. Finally, we discuss open research challenges.

Problem

• Using LLMs to detect mobile app security risks
• Applying LLMs to prevent privacy violations in apps
• Exploring LLMs to replace traditional mobile app analysis

Innovation

• LLMs detect mobile app security risks
• LLMs replace traditional analysis methods
• LLMs prevent sensitive data leakage