Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Dayong, Zhu, Tainqing, Zhu, Congcong, He, Feng, He, Qi, Wang, Shang, Liu, Bo, Zhou, Wanlei
Format:	Preprint
Published:	2026
Subjects:	Multiagent Systems Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2604.00430