A Visual Analytics Framework for Adversarial Text Generation

09/24/2019
by   Brandon Laughlin, et al.
0

This paper presents a framework which enables a user to more easily make corrections to adversarial texts. While attack algorithms have been demonstrated to automatically build adversaries, changes made by the algorithms can often have poor semantics or syntax. Our framework is designed to facilitate human intervention by aiding users in making corrections. The framework extends existing attack algorithms to work within an evolutionary attack process paired with a visual analytics loop. Using an interactive dashboard a user is able to review the generation process in real time and receive suggestions from the system for edits to be made. The adversaries can be used to both diagnose robustness issues within a single classifier or to compare various classifier options. With the weaknesses identified, the framework can also be used as a first step in mitigating adversarial threats. The framework can be used as part of further research into defense methods in which the adversarial examples are used to evaluate new countermeasures. We demonstrate the framework with a word swapping attack for the task of sentiment classification.

READ FULL TEXT

page 5

page 9

research
10/05/2020

CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation

NLP models are shown to suffer from robustness issues, i.e., a model's p...
research
03/22/2021

Grey-box Adversarial Attack And Defence For Sentiment Classification

We introduce a grey-box adversarial attack and defence framework for sen...
research
03/10/2020

Generating Natural Language Adversarial Examples on a Large Scale with Generative Models

Today text classification models have been widely used. However, these c...
research
10/25/2021

Generating Watermarked Adversarial Texts

Adversarial example generation has been a hot spot in recent years becau...
research
08/27/2022

Adversarial Robustness for Tabular Data through Cost and Utility Awareness

Many machine learning problems use data in the tabular domains. Adversar...
research
05/04/2022

Rethinking Classifier and Adversarial Attack

Various defense models have been proposed to resist adversarial attack a...
research
08/07/2020

Visual Attack and Defense on Text

Modifying characters of a piece of text to their visual similar ones oft...

Please sign up or login with your details

Forgot password? Click here to reset