Generating Textual Adversaries with Minimal Perturbation

11/12/2022
by   Xingyi Zhao, et al.
0

Many word-level adversarial attack approaches for textual data have been proposed in recent studies. However, due to the massive search space consisting of combinations of candidate words, the existing approaches face the problem of preserving the semantics of texts when crafting adversarial counterparts. In this paper, we develop a novel attack strategy to find adversarial texts with high similarity to the original texts while introducing minimal perturbation. The rationale is that we expect the adversarial texts with small perturbation can better preserve the semantic meaning of original texts. Experiments show that, compared with state-of-the-art attack approaches, our approach achieves higher success rates and lower perturbation rates in four benchmark datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/03/2022

SemAttack: Natural Textual Attacks via Different Semantic Spaces

Recent studies show that pre-trained language models (LMs) are vulnerabl...
research
05/22/2022

Phrase-level Textual Adversarial Attack with Label Preservation

Generating high-quality textual adversarial examples is critical for inv...
research
11/17/2022

UPTON: Unattributable Authorship Text via Data Poisoning

In online medium such as opinion column in Bloomberg, The Guardian and W...
research
11/02/2021

HydraText: Multi-objective Optimization for Adversarial Textual Attack

The field of adversarial textual attack has significantly grown over the...
research
01/22/2018

Adversarial Texts with Gradient Methods

Adversarial samples for images have been extensively studied in the lite...
research
07/03/2019

Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack

The evaluation of robustness against adversarial manipulation of neural ...

Please sign up or login with your details

Forgot password? Click here to reset