Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Boyang, Akkus, Istemi Ekin, Chen, Ruichuan, Dethise, Alice, Satzke, Klaus, Rimac, Ivica, Zhang, Yang
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.25525