ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Lu Yan, Zhuo Zhang 0002, Guanhong Tao 0001, Kaiyuan Zhang 0002, Xuan Chen, Guangyu Shen, Xiangyu Zhang. ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]

This author has not been identified. Look up 'Lu Yan' in GoogleThis author has not been identified. Look up 'Zhuo Zhang 0002' in GoogleThis author has not been identified. Look up 'Guanhong Tao 0001' in GoogleThis author has not been identified. Look up 'Kaiyuan Zhang 0002' in GoogleThis author has not been identified. Look up 'Xuan Chen' in GoogleThis author has not been identified. Look up 'Guangyu Shen' in GoogleThis author has not been identified. Look up 'Xiangyu Zhang' in Google

runs on WebDSL