LLMs在移动应用隐私与安全支持中的研究：现状与未来方向 (LLMs on support of privacy and security of mobile apps: state of the art and research directions)

from arxiv, I am writing to respectfully request the withdrawal of my recent submission to arXiv due to an authorship issue. The paper was submitted without the explicit consent of two co-authors. After internal discussion, they have expressed clear disagreement with the submission and raised concerns about unresolved academic inaccuracies in the current version

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.

翻译：现代生活见证了移动设备的爆炸式增长。然而，除了为用户带来便利的宝贵功能外，安全与隐私风险仍持续威胁着移动应用用户。近年来，这些威胁日益复杂化，突显了对更先进、高效检测方法的迫切需求。本章探讨了大型语言模型（LLMs）在移动应用生态系统中识别安全风险与隐私侵犯行为并实施缓解的应用。通过介绍将LLMs应用于缓解智能手机平台十大常见安全风险的前沿研究，我们强调了LLMs替代传统分析方法的可行性与潜力，例如移动应用的动态分析与混合分析。作为基于LLM解决方案的代表性案例，我们提出了一种检测用户在线分享图像时敏感数据泄露的方法，这是当前智能手机用户的常见行为。最后，我们讨论了开放的研究挑战。