Williams, Kai
- Representation Noising: A Defence Mechanism Against Harmful Finetuning
2024/05/23 by Domenic Rosati, Rosati, Domenic, J.M. Wehner +17 · 20 citations
Decision Sciences · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Scientific Computing and Data Management
- Immunization against harmful fine-tuning attacks
2024/02/26 by Rosati, Domenic, Wehner, Jan, Williams, Kai +4 · 7 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences