Poster: Cloudsweeper: Leveraging Large Language Models to Personalize Sensitive Archive Search
Publication Date
8-27-2025
Document Type
Conference Proceeding
Publication Title
2025 Silicon Valley Cybersecurity Conference Svcc 2025
DOI
10.1109/SVCC65277.2025.11133628
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.
Keywords
Archive Search, Cybersecurity, Large Language Models, Retrieval-Augmented Generation, User Privacy
Department
Computer Engineering
Recommended Citation
Victor Escuerdo, Sergio Talavera, Gautam Santhanu Thampy, Ivan Torres, Daniel Vega Lojo, Chris Kanich, and Magdalini Eirinaki. "Poster: Cloudsweeper: Leveraging Large Language Models to Personalize Sensitive Archive Search" 2025 Silicon Valley Cybersecurity Conference Svcc 2025 (2025). https://doi.org/10.1109/SVCC65277.2025.11133628
