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]
@inproceedings{Yan000CSZ23, title = {ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP}, author = {Lu Yan and Zhuo Zhang 0002 and Guanhong Tao 0001 and Kaiyuan Zhang 0002 and Xuan Chen and Guangyu Shen and Xiangyu Zhang}, year = {2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/d2b752ed4726286a4b488ae16e091d64-Abstract-Conference.html}, researchr = {https://researchr.org/publication/Yan000CSZ23}, cites = {0}, citedby = {0}, booktitle = {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}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, }