Showing 1 - 4 of 4
Persistent link: https://www.econbiz.de/10003912257
Persistent link: https://www.econbiz.de/10001557115
Persistent link: https://www.econbiz.de/10001826695
We propose algorithms to create adversarial attacks to assess model robustness in text classification problems. They can be used to create white box attacks and black box attacks while at the same time preserving the semantics and syntax of the original text. The attacks cause significant number...
Persistent link: https://www.econbiz.de/10012825215