Back to Search
Start Over
CRank: Reusable Word Importance Ranking for Text Adversarial Attack
- Source :
- Applied Sciences, Vol 11, Iss 20, p 9570 (2021)
- Publication Year :
- 2021
- Publisher :
- MDPI AG, 2021.
-
Abstract
- Deep learning models have been widely used in natural language processing tasks, yet researchers have recently proposed several methods to fool the state-of-the-art neural network models. Among these methods, word importance ranking is an essential part that generates text adversarial examples, but suffers from low efficiency for practical attacks. To address this issue, we aim to improve the efficiency of word importance ranking, making steps towards realistic text adversarial attacks. In this paper, we propose CRank, a black box method utilized by our innovated masking and ranking strategy. CRank improves efficiency by 75% at the ’cost’ of only a 1% drop of the success rate when compared to the classic method. Moreover, we explore a new greedy search strategy and Unicode perturbation methods.
Details
- Language :
- English
- ISSN :
- 20763417
- Volume :
- 11
- Issue :
- 20
- Database :
- Directory of Open Access Journals
- Journal :
- Applied Sciences
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.1d31471ccda4544911ab0aabfcb10ed
- Document Type :
- article
- Full Text :
- https://doi.org/10.3390/app11209570