Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots

Item #:

075280-3199

Details

DOI: https://doi.org/10.52202/075280-3199
Author(s): Rui Chen, Xia Hu, Yiming Li, Zirui Liu, Ruixiang (Ryan) Tang, Jiayi Yuan
Pages: 73191-73210 (20 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/075280-3199
Author(s): Rui Chen, Xia Hu, Yiming Li, Zirui Liu, Ruixiang (Ryan) Tang, Jiayi Yuan
Pages: 73191-73210 (20 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)