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

03/10/2020
by   Yankun Ren, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/04/2020

BAE: BERT-based Adversarial Examples for Text Classification

Modern text classification models are susceptible to adversarial example...
research
07/24/2023

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models

Unrestricted adversarial attacks present a serious threat to deep learni...
research
08/21/2023

Feature Extraction Using Deep Generative Models for Bangla Text Classification on a New Comprehensive Dataset

The selection of features for text classification is a fundamental task ...
research
09/24/2019

A Visual Analytics Framework for Adversarial Text Generation

This paper presents a framework which enables a user to more easily make...
research
11/22/2017

Safer Classification by Synthesis

The discriminative approach to classification using deep neural networks...
research
12/13/2018

TextBugger: Generating Adversarial Text Against Real-world Applications

Deep Learning-based Text Understanding (DLTU) is the backbone technique ...
research
12/22/2019

AdvCodec: Towards A Unified Framework for Adversarial Text Generation

While there has been great interest in generating imperceptible adversar...

Please sign up or login with your details

Forgot password? Click here to reset