Xiaoyi Chen, Ahmed Salem 0001, Dingfan Chen, Michael Backes 0001, ShiQing Ma, Qingni Shen, Zhonghai Wu, Yang Zhang 0016. BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements. In ACSAC '21: Annual Computer Security Applications Conference, Virtual Event, USA, December 6 - 10, 2021. pages 554-569, ACM, 2021. [doi]
Abstract is missing.