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...

Full description

Bibliographic Details
Main Authors: Vijayaraghavan, P, Roy, D
Other Authors: Massachusetts Institute of Technology. Media Laboratory
Format: Article
Language:English
Published: Springer International Publishing 2021
Online Access:https://hdl.handle.net/1721.1/137065