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...
| Main Authors: | , |
|---|---|
| Drugi avtorji: | |
| Format: | Article |
| Jezik: | English |
| Izdano: |
Springer International Publishing
2021
|
| Online dostop: | https://hdl.handle.net/1721.1/137065 |