notesum.ai

Published at November 14

DROJ: A Prompt-Driven Attack against Large Language Models

cs.CL

cs.AI

Released Date: November 14, 2024

Authors: Leyang Hu¹, Boran Wang¹

Aff.: ¹Department of Computer Science, Brown University

Arxiv: http://arxiv.org/abs/2411.09125v1

Refer to caption

Refer to caption

Refer to caption