Hanbin Hong
Hanbin Hong
Home
Publications
Projects
Contact
Light
Dark
Automatic
2
Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
We propose a framework to guarantee the certifiable robustness of language model against multiple practical attacks in NLP.
Xinyu Zhang
,
Hanbin Hong
,
Yuan Hong
,
Peng Huang
,
Binghui Wang
,
Zhongjie Ba
,
Kui Ren
Cite
Cite
×