Generating Black-Box Adversarial Examples for Text Classifiers Using a Deep Reinforced Model
© Springer Nature Switzerland AG 2020. Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by applying adversarial t...
| Autors principals: | , |
|---|---|
| Altres autors: | |
| Format: | Article |
| Idioma: | English |
| Publicat: |
Springer International Publishing
2021
|
| Accés en línia: | https://hdl.handle.net/1721.1/137065 |