Representation Noising: A Defence Mechanism Against Harmful Finetuning

Item #:

079017-0402

Details

DOI: https://doi.org/10.52202/079017-0402
Author(s): David Atanasov, Łukasz Bartoszcze, Robie Gonzales, Subhabrata Majumdar, Carsten Maple, Domenic Rosati, Frank Rudzicz, Hassan Sajjad, Jan Wehner, Kai Williams
Pages: 12636-12676 (41 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/10.52202/079017-0402
Author(s): David Atanasov, Łukasz Bartoszcze, Robie Gonzales, Subhabrata Majumdar, Carsten Maple, Domenic Rosati, Frank Rudzicz, Hassan Sajjad, Jan Wehner, Kai Williams
Pages: 12636-12676 (41 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)