Dissecting Adversarial Robustness of Multimodal LM Agents

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components, which existing LM safety evaluations do not adequately address. To bridge this...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Wu, Chen Henry, Shah, Rishi, Koh, Jing Yu, Salakhutdinov, Ruslan, Fried, Daniel, Raghunathan, Aditi
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition Computer Science - Cryptography and Security Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!