Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses

Item #:

079017-1034

Details

DOI: https://doi.org/10.52202/079017-1034
Author(s): Chao Du, Jing Jiang, Min Lin, Qian Liu, Tianyu Pang, Xiaosen Zheng
Pages: 32856-32887 (32 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/079017-1034
Author(s): Chao Du, Jing Jiang, Min Lin, Qian Liu, Tianyu Pang, Xiaosen Zheng
Pages: 32856-32887 (32 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 37
Date/Location: Held 10-15 December 2024, Vancouver, Canada.
Series: Advances in Neural Information Processing Systems 37
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)