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

• URL: http://arxiv.org/abs/2506.11679v2
• Date: Mon, 07 Jul 2025 17:36:57 GMT
• Title: LLMs on support of privacy and security of mobile apps: state of the art and research directions
• Authors: Tran Thanh Lam Nguyen, Barbara Carminati, Elena Ferrari,
• Abstract summary: Security and privacy risks still threaten users of mobile apps.<n>We explore the application of Large Language Models to identify security risks and privacy violations.<n>We present an approach to detect sensitive data leakage when users share images online.
• Score: 1.5293427903448022
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography [77.44136793431893]
  We propose a novel jailbreak paradigm that introduces dual steganography to covertly embed malicious queries into benign-looking images.<n>Our Odysseus successfully jailbreaks several pioneering and realistic MLLM-integrated systems, achieving up to 99% attack success rate.
  arXiv  Detail & Related papers  (2025-12-23T08:53:36Z)
• OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows [77.95511352806261]
  Computer-using agents powered by Vision-Language Models (VLMs) have demonstrated human-like capabilities in operating digital environments like mobile platforms.<n>We propose OS-Sentinel, a novel hybrid safety detection framework that combines a Formal Verifier for detecting explicit system-level violations with a Contextual Judge for assessing contextual risks and agent actions.
  arXiv  Detail & Related papers  (2025-10-28T13:22:39Z)
• Beyond Data Privacy: New Privacy Risks for Large Language Models [37.95953819924652]
  Large Language Models (LLMs) have achieved remarkable progress in natural language understanding, reasoning, and autonomous decision-making.<n>These advancements have also come with significant privacy concerns.<n>The integration of LLMs into widely used applications and the weaponization of their autonomous abilities have created new privacy vulnerabilities.
  arXiv  Detail & Related papers  (2025-09-16T09:46:09Z)
• A Survey: Towards Privacy and Security in Mobile Large Language Models [17.927458870623095]
  Mobile Large Language Models (LLMs) are revolutionizing diverse fields such as healthcare, finance, and education with their ability to perform advanced natural language processing tasks on-the-go.<n>However, the deployment of these models in mobile and edge environments introduces significant challenges related to privacy and security due to their resource-intensive nature and the sensitivity of the data they process.<n>This survey provides a comprehensive overview of privacy and security issues associated with mobile LLMs, systematically categorizing existing solutions such as differential privacy, federated learning, and prompt encryption.
  arXiv  Detail & Related papers  (2025-09-02T15:19:57Z)
• A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives [65.3369988566853]
  Recent studies have demonstrated that adversaries can replicate a target model's functionality.<n>Model Extraction Attacks pose threats to intellectual property, privacy, and system security.<n>We propose a novel taxonomy that classifies MEAs according to attack mechanisms, defense approaches, and computing environments.
  arXiv  Detail & Related papers  (2025-08-20T19:49:59Z)
• Large AI Model-Enabled Secure Communications in Low-Altitude Wireless Networks: Concepts, Perspectives and Case Study [92.15255222408636]
  Low-altitude wireless networks (LAWNs) have the potential to revolutionize communications by supporting a range of applications.<n>We investigate some large artificial intelligence model (LAM)-enabled solutions for secure communications in LAWNs.<n>To demonstrate the practical benefits of LAMs for secure communications in LAWNs, we propose a novel LAM-based optimization framework.
  arXiv  Detail & Related papers  (2025-08-01T01:53:58Z)
• A Survey on Privacy Risks and Protection in Large Language Models [13.602836059584682]
  Large Language Models (LLMs) have become increasingly integral to diverse applications, raising privacy concerns.<n>This survey offers a comprehensive overview of privacy risks associated with LLMs and examines current solutions to mitigate these challenges.
  arXiv  Detail & Related papers  (2025-05-04T03:04:07Z)
• LLMs in Mobile Apps: Practices, Challenges, and Opportunities [4.104646810514711]
  The integration of AI techniques has become increasingly popular in software development.<n>With the rise of large language models (LLMs) and generative AI, developers now have access to a wealth of high-quality open-source models and APIs from closed-source providers.
  arXiv  Detail & Related papers  (2025-02-21T19:53:43Z)
• The Information Security Awareness of Large Language Models [13.977080888159627]
  Information security awareness (ISA) is an important yet underexplored safety aspect of large language models (LLMs)<n>We present an automated method for measuring the ISA of LLMs, which covers all 30 security topics in a mobile ISA taxonomy.<n>We find that most of the popular models exhibit only medium to low levels of ISA, exposing their users to cybersecurity threats.
  arXiv  Detail & Related papers  (2024-11-20T11:09:55Z)
• Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents [67.07177243654485]
  This survey collects and analyzes the different threats faced by large language models-based agents. We identify six key features of LLM-based agents, based on which we summarize the current research progress. We select four representative agents as case studies to analyze the risks they may face in practical use.
  arXiv  Detail & Related papers  (2024-11-14T15:40:04Z)
• The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies [43.65655064122938]
  Large Language Models (LLMs) agents have evolved to perform complex tasks. The widespread applications of LLM agents demonstrate their significant commercial value. However, they also expose security and privacy vulnerabilities. This survey aims to provide a comprehensive overview of the newly emerged privacy and security issues faced by LLM agents.
  arXiv  Detail & Related papers  (2024-07-28T00:26:24Z)
• "Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models [74.05368440735468]
  Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases.
  arXiv  Detail & Related papers  (2024-06-26T05:36:23Z)
• Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications [37.316238236750415]
  Large language models (LLMs) are increasingly deployed as the service backend for LLM-integrated applications. In this work, we consider a setup where the user and LLM interact via an LLM-integrated application in the middle. We identify potential vulnerabilities that can originate from the malicious application developer or from an outsider threat. We develop a lightweight, threat-agnostic defense that mitigates both insider and outsider threats.
  arXiv  Detail & Related papers  (2023-11-07T20:13:05Z)
• Privacy in Large Language Models: Attacks, Defenses and Future Directions [84.73301039987128]
  We analyze the current privacy attacks targeting large language models (LLMs) and categorize them according to the adversary's assumed capabilities. We present a detailed overview of prominent defense strategies that have been developed to counter these privacy attacks.
  arXiv  Detail & Related papers  (2023-10-16T13:23:54Z)
• Vulnerability of Machine Learning Approaches Applied in IoT-based Smart Grid: A Review [51.31851488650698]
  Machine learning (ML) sees an increasing prevalence of being used in the internet-of-things (IoT)-based smart grid. adversarial distortion injected into the power signal will greatly affect the system's normal control and operation. It is imperative to conduct vulnerability assessment for MLsgAPPs applied in the context of safety-critical power systems.
  arXiv  Detail & Related papers  (2023-08-30T03:29:26Z)
• Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection [64.67495502772866]
  Large Language Models (LLMs) are increasingly being integrated into various applications. We show how attackers can override original instructions and employed controls using Prompt Injection attacks. We derive a comprehensive taxonomy from a computer security perspective to systematically investigate impacts and vulnerabilities.
  arXiv  Detail & Related papers  (2023-02-23T17:14:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.