Unicode Evil: Evading NLP Systems Using Visual Similarities of Text Characters - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Antreas Dionysiou, Elias Athanasopoulos. Unicode Evil: Evading NLP Systems Using Visual Similarities of Text Characters. In Nicholas Carlini, Ambra Demontis, Yizheng Chen, editors, AISec@CCS 2021: Proceedings of the 14th ACM Workshop on Artificial Intelligence and Security, Virtual Event, Republic of Korea, 15 November 2021. pages 1-12, ACM, 2021. [doi]

This author has not been identified. Look up 'Antreas Dionysiou' in GoogleThis author has not been identified. Look up 'Elias Athanasopoulos' in Google

runs on WebDSL