"Distilling Adversarial Prompts from Safety Benchmarks: Report for the ..."

Manuel Brack, Patrick Schramowski, Kristian Kersting (2023)

Details and statistics

DOI: 10.48550/ARXIV.2309.11575

access: open

type: Informal or Other Publication

metadata version: 2023-09-25

a service of  Schloss Dagstuhl - Leibniz Center for Informatics