Towards Evaluating the Robustness of Chinese BERT Classifiers

04/07/2020
by   Boxin Wang, et al.
0

Recent advances in large-scale language representation models such as BERT have improved the state-of-the-art performances in many NLP tasks. Meanwhile, character-level Chinese NLP models, including BERT for Chinese, have also demonstrated that they can outperform the existing models. In this paper, we show that, however, such BERT-based models are vulnerable under character-level adversarial attacks. We propose a novel Chinese char-level attack method against BERT-based classifiers. Essentially, we generate "small" perturbation on the character level in the embedding space and guide the character substitution procedure. Extensive experiments show that the classification accuracy on a Chinese news dataset drops from 91.8 than 2 characters on average based on the proposed attack. Human evaluations also confirm that our generated Chinese adversarial examples barely affect human performance on these NLP tasks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

08/31/2017

Glyph-aware Embedding of Chinese Characters

Given the advantage and recent success of English character-level and su...
10/12/2020

EFSG: Evolutionary Fooling Sentences Generator

Large pre-trained language representation models (LMs) have recently col...
08/10/2020

FireBERT: Hardening BERT-based classifiers against adversarial attack

We present FireBERT, a set of three proof-of-concept NLP classifiers har...
02/23/2021

Enhancing Model Robustness By Incorporating Adversarial Knowledge Into Semantic Representation

Despite that deep neural networks (DNNs) have achieved enormous success ...
06/02/2021

BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks

Adversarial attacks expose important blind spots of deep learning system...
04/26/2020

SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check

Chinese Spelling Check (CSC) is a task to detect and correct spelling er...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.