Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/137428
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Backdoors Against Natural Language Processing: A Review |
Author: | Li, S. Dong, T. Zhao, B.Z.H. Xue, M. Du, S. Zhu, H. |
Citation: | IEEE Security and Privacy Magazine, 2022; 20(5):50-59 |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Issue Date: | 2022 |
ISSN: | 1540-7993 1558-4046 |
Statement of Responsibility: | Shaofeng Li, Tian Dong, Benjamin Zi Hao Zhao, Minhui Xue Suguo Du and Haojin Zhu |
Abstract: | Data poisoning attacks, specifically backdoor attacks, present a severe security threat in artificial intelligence. We provide a comprehensive survey into state-of-the-art backdoor attacks and defenses in the field of natural language processing. |
Rights: | © 2022, IEEE |
DOI: | 10.1109/MSEC.2022.3181001 |
Grant ID: | http://purl.org/au-research/grants/arc/DP210102670 |
Published version: | http://dx.doi.org/10.1109/msec.2022.3181001 |
Appears in Collections: | Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.