Quantifying the Performance of Adversarial Training on Language Models with Distribution Shifts

Published in In the proceedings of CySSS@AsiaCCS'22: Proceedings of the 1st Workshop on Cybersecurity and Social Sciences, Nagasaki, Japan, 30 May 2022, 2022

Recommended citation: Marwan Omar, Soohyeon Choi, Daehun Nyang, David Mohaisen, "Quantifying the Performance of Adversarial Training on Language Models with Distribution Shifts." In Proceedings of the 1st Workshop on Cybersecurity and Social Sciences (CySSS@AsiaCCS), Nagasaki, Japan, 2022.