Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Alizadeh, Meysam, Samei, Zeynab, Stetsenko, Daria, Gilardi, Fabrizio
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computation and Language 68Txx
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2506.01055