5 citations · 11 across the 8 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022
A3T: Accuracy Aware Adversarial Training
Enes Altinisik, Safa Messaoud, Husrev Taha Sencar +1
Adversarial training has been empirically shown to be more prone to overfitting than standard training. The exact underlying reasons still need to be fully understood. In this pape…
cs.CL2022★ 1 cited
Impact of Adversarial Training on Robustness and Generalizability of Language Models
Enes Altinisik, Hassan Sajjad, Husrev Taha Sencar +2
Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and gener…