A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples


Loading...

Date

2020-12

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Generating adversarial examples for natural language is hard, as natural language consists of discrete symbols, and examples are often of variable lengths. In this paper, we propose a geometry-inspired attack for generating natural language adversarial examples. Our attack generates adversarial examples by iteratively approximating the decision boundary of Deep Neural Networks (DNNs). Experiments on two datasets with two different models show that our attack fools natural language models with high success rates, while only replacing a few words. Human evaluation shows that adversarial examples generated by our attack are hard for humans to recognize. Further experiments show that adversarial training can improve model robustness against our attack.

Publication status

published

Book title

Proceedings of the 28th International Conference on Computational Linguistics

Journal / series

Volume

Pages / Article No.

6679 - 6689

Publisher

International Committee on Computational Linguistics

Event

28th International Conference on Computational Linguistics (COLING 2020) (virtual)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03604 - Wattenhofer, Roger / Wattenhofer, Roger check_circle

Notes

Due to the Coronavirus (COVID-19) the conference was conducted virtually.

Funding

Related publications and datasets