Understanding and Detecting File Knowledge Leakage in GPT App Ecosystem
OpenAI has enabled third-party developers to build applications around ChatGPT, known as GPTs, to expand its capability to handle complex and specialized tasks. A key feature of GPTs is Retrieval-Augmented Generation (RAG), which allows developers to upload documents containing domain knowledge or application context, referred to as file knowledge. However, these documents often contain sensitive information, and the security mechanisms governing access control in GPTs remains an underexplored area.
Authors
- Guangdong Bai (ORCID: https://orcid.org/0000-0002-6390-9890)
- Chuan Yan (ORCID: https://orcid.org/0000-0003-4855-1912)
- Liuhuo Wan (ORCID: https://orcid.org/0009-0004-7090-1493)
- Y.S Li
- Mark Huasong Meng (ORCID: https://orcid.org/0000-0003-1039-2151)
- Bowei Guan
Institutions
- The University of Queensland (AU)
- Technical University of Munich (DE)
Publication Details
- Published
- 2025-04-22
- DOI
- https://doi.org/10.1145/3696410.3714755
- Citations
- 1
- Primary Topic
- Advanced Data Storage Technologies
- Type
- article
- Field-Weighted Citation Impact
- 1.49