notesum.ai

Published at November 12

Can adversarial attacks by large language models be attributed?

cs.AI
cs.CL
cs.CY
cs.FL

Released Date: November 12, 2024

Authors: Manuel Cebrian1, Jan Arne Telle2

Aff.: 1Center for Automation and Robotics, Spanish National Research Council; 2Department of Informatics, University of Bergen

Arxiv: http://arxiv.org/abs/2411.08003v1