Adversarial Attacks in Textual Deep Neural Networks

Author(s): Edward Ma

Originally published on Towards AI.

What is an adversarial attack?

Photo by Solal Ohayon on Unsplash

Adversarial examples aim at causing target model to make a mistake on prediction. It can be either be intended or unintended to cause a model to perform poorly. For example, we may have a typo when using Gmail and making Smart Reply unable to provide a suggestion for writing an email.

No matter it is an intentional or unintentional adversarial attack, evaluating adversarial examples has become a trend of building a robust deep learning model and understanding the shortcomings of models. This story will talk about the adversarial attacks and how we can generate adversarial examples… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI