5 citations · 5 across the 2 of their papers we have counts for
2 papers
cs.CL2022
Improving robustness of language models from a geometry-aware perspective
Bin Zhu, Zhaoquan Gu, Le Wang +2
Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness. However, we observe th…
cs.LG2021★ 5 cited
TREATED:Towards Universal Defense against Textual Adversarial Attacks
Bin Zhu, Zhaoquan Gu, Le Wang +1
Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critica…