Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space

Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of open-source models. As open-source models advance in capabili...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Schwinn, Leo, Dobre, David, Xhonneux, Sophie, Gidel, Gauthier, Gunnemann, Stephan
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!