"Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game."

Sam Toyer et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2311.01011

access: open

type: Informal or Other Publication

metadata version: 2023-11-07

a service of  Schloss Dagstuhl - Leibniz Center for Informatics