A Survey: Towards Privacy and Security in Mobile Large Language Models
It addresses privacy and security problems for developers and users of mobile LLMs in fields like healthcare and finance, but it is incremental as a survey that synthesizes existing knowledge without introducing new methods.
This survey tackles the privacy and security challenges in mobile large language models (LLMs) by providing a comprehensive overview of issues and systematically categorizing existing solutions like differential privacy and federated learning, while analyzing vulnerabilities such as adversarial attacks and proposing future research directions.
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. 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. 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. Furthermore, we analyze vulnerabilities unique to mobile LLMs, including adversarial attacks, membership inference, and side-channel attacks, offering an in-depth comparison of their effectiveness and limitations. Despite recent advancements, mobile LLMs face unique hurdles in achieving robust security while maintaining efficiency in resource-constrained environments. To bridge this gap, we propose potential applications, discuss open challenges, and suggest future research directions, paving the way for the development of trustworthy, privacy-compliant, and scalable mobile LLM systems.