DeepAI
Log In Sign Up

Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers

01/13/2018
by   Ji Gao, et al.
0

Although various techniques have been proposed to generate adversarial samples for white-box attacks on text, little attention has been paid to a black-box attack, which is a more realistic scenario. In this paper, we present a novel algorithm, DeepWordBug, to effectively generate small text perturbations in a black-box setting that forces a deep-learning classifier to misclassify a text input. We develop novel scoring strategies to find the most important words to modify such that the deep classifier makes a wrong prediction. Simple character-level transformations are applied to the highest-ranked words in order to minimize the edit distance of the perturbation. We evaluated DeepWordBug on two real-world text datasets: Enron spam emails and IMDB movie reviews. Our experimental results indicate that DeepWordBug can reduce the classification accuracy from 99% to around 40% on Enron data and from 87% to about 26% on IMDB. Also, our experimental results strongly demonstrate that the generated adversarial sequences from a deep-learning model can similarly evade other deep models.

READ FULL TEXT

page 1

page 2

page 3

page 4

08/16/2020

TextDecepter: Hard Label Black Box Attack on Text Classifiers

Machine learning has been proven to be susceptible to carefully crafted ...
04/30/2022

Optimizing One-pixel Black-box Adversarial Attacks

The output of Deep Neural Networks (DNN) can be altered by a small pertu...
05/07/2019

Transparent pronunciation scoring using articulatorily weighted phoneme edit distance

For researching effects of gamification in foreign language learning for...
07/10/2017

Towards Crafting Text Adversarial Samples

Adversarial samples are strategically modified samples, which are crafte...
09/24/2021

AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses

Deep-learning based Automatic Essay Scoring (AES) systems are being acti...
11/01/2021

Logic Rules Meet Deep Learning: A Novel Approach for Ship Type Classification

The shipping industry is an important component of the global trade and ...
09/14/2021

PETGEN: Personalized Text Generation Attack on Deep Sequence Embedding-based Classification Models

What should a malicious user write next to fool a detection model? Ident...