DeepAI AI Chat
Log In Sign Up

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

by   Yankun Ren, et al.
University of Southern California

Today text classification models have been widely used. However, these classifiers are found to be easily fooled by adversarial examples. Fortunately, standard attacking methods generate adversarial texts in a pair-wise way, that is, an adversarial text can only be created from a real-world text by replacing a few words. In many applications, these texts are limited in numbers, therefore their corresponding adversarial examples are often not diverse enough and sometimes hard to read, thus can be easily detected by humans and cannot create chaos at a large scale. In this paper, we propose an end to end solution to efficiently generate adversarial texts from scratch using generative models, which are not restricted to perturbing the given texts. We call it unrestricted adversarial text generation. Specifically, we train a conditional variational autoencoder (VAE) with an additional adversarial loss to guide the generation of adversarial examples. Moreover, to improve the validity of adversarial texts, we utilize discrimators and the training framework of generative adversarial networks (GANs) to make adversarial texts consistent with real data. Experimental results on sentiment analysis demonstrate the scalability and efficiency of our method. It can attack text classification models with a higher success rate than existing methods, and provide acceptable quality for humans in the meantime.


page 1

page 2

page 3

page 4


BAE: BERT-based Adversarial Examples for Text Classification

Modern text classification models are susceptible to adversarial example...

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...

Is BERT Really Robust? Natural Language Attack on Text Classification and Entailment

Machine learning algorithms are often vulnerable to adversarial examples...

A Visual Analytics Framework for Adversarial Text Generation

This paper presents a framework which enables a user to more easily make...

Safer Classification by Synthesis

The discriminative approach to classification using deep neural networks...

TextBugger: Generating Adversarial Text Against Real-world Applications

Deep Learning-based Text Understanding (DLTU) is the backbone technique ...

Robust Text CAPTCHAs Using Adversarial Examples

CAPTCHA (Completely Automated Public Truing test to tell Computers and H...