arXiv AI By V\'aclav Jane\v{c}ek, Thomas Melham

Privilege and confidentiality in generative AI workflows

Read the original on arXiv AI →

arXiv:2607. 05479v1 Announce Type: cross Abstract: Generative AI (GenAI) systems store and process client data in three distinct ways: in the model's parameters through training and memorisation, in the context window during a live session, and in knowledge databases for retrieval-augmented generation (RAG).

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jun 17

An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios

arXiv:2606. 17114v1 Announce Type: cross Abstract: AI agents are increasingly being adopted in enterprise and personal settings with access to emails, databases, documents, and other tools where they can read, update, and disseminate sensitive information.

By Hankyul Baek, Jaewon Noh, Sang Seo, Yongsu Kim, Gabriel Waikin Loh Matienzo, Young Il Kim, Ee Wei Seah, Akriti Vij