Unveiling the Vulnerability of Private Fine-Tuning in Split-Based Frameworks for Large Language Models: A Bidirectionally Enhanced Attack

Recent advancements in pre-trained large language models (LLMs) have significantly influenced various domains. Adapting these models for specific tasks often involves fine-tuning (FT) with private, domain-specific data. However, privacy concerns keep this data undisclosed, and the computational dema...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-09
Hauptverfasser:	Chen, Guanzhong, Qin, Zhenghan, Yang, Mingxin, Zhou, Yajie, Fan, Tao, Du, Tianyu, Xu, Zenglin
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Cryptography and Security Large language models Privacy Reconstruction
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!