PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps

The pre-training and fine-tuning paradigm has demonstrated its effectiveness and has become the standard approach for tailoring language models to various tasks. Currently, community-based platforms offer easy access to various pre-trained models, as anyone can publish without strict validation proc...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings of the ... ACM Conference on Computer and Communications Security Jg. 2024; S. 3511
Hauptverfasser:	Liu, Ruixuan, Wang, Tianhao, Cao, Yang, Xiong, Li
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States 01.10.2024
Schlagworte:	Pre-Training Language Model Privacy Attack
ISSN:	1543-7221, 1543-7221
Online-Zugang:	Weitere Angaben
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!