Poster: Cloudsweeper: Leveraging Large Language Models to Personalize Sensitive Archive Search
Abstract
As cyber threats continue to evolve, overlooked or neglected files stored in cloud services can pose significant risks to personal privacy and data security. In this paper we present Cloudsweeper, a system that aims to improve cloud storage security by creating tools that help users identify and manage sensitive or unwanted files. Cloudsweeper leverages Large Language Models (LLMs) with a Retrieval-Augmented Generation (RAG) architecture to develop a personalized and privacy-focused archive search system. Cloudsweeper represents an innovative approach to secure archive management, balancing user control and privacy in cloud storage environments.
This paper has been withdrawn.
