1. Evaluating and Certifying the Adversarial Robustness of Neural Language Models Open Access Author: Ye, Muchao Title: Evaluating and Certifying the Adversarial Robustness of Neural Language Models Graduate Program: Informatics Keywords: Adversarial RobustnessNeural Language Models File: Download final.pdf Committee Members: Dongwon Lee, Professor in Charge/Director of Graduate StudiesFenglong Ma, Chair & Dissertation AdvisorRui Zhang, Outside Unit & Field MemberTing Wang, Major Field MemberJinghui Chen, Major Field Member
