FastTextDodger: Decision-Based Adversarial Attack Against Black-Box NLP Models With Extremely High Efficiency-Reference-Cited by-同舟云学术

FastTextDodger: Decision-Based Adversarial Attack Against Black-Box NLP Models With Extremely High Efficiency

Published:2024 Issue: Volume:19 Page:2398-2411
ISSN:1556-6013
Container-title:IEEE Transactions on Information Forensics and Security
language:
Short-container-title:IEEE Trans.Inform.Forensic Secur.

Author:

Hu Xiaoxue¹,Liu Geling¹,Zheng Baolin²,Zhao Lingchen¹^ORCID,Wang Qian¹^ORCID,Zhang Yufei³,Du Minxin⁴^ORCID

Affiliation:

1. Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan, China

2. Alibaba Group, Beijing, China

3. Department of Computer Science, ETH Zürich, Zürich, Switzerland

4. Department of Information Engineering, The Chinese University of Hong Kong, Ma Liu Shui, Hong Kong

Funder

NSFC

Fundamental Research Funds for the Central Universities

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx7/10206/10319981/10381813.pdf?arnumber=10381813

Reference45 articles.

1. Explaining and harnessing adversarial examples;Goodfellow

2. HopSkipJumpAttack: A Query-Efficient Decision-Based Attack

3. Practical Hidden Voice Attacks against Speech and Speaker Recognition Systems

4. HotFlip: White-Box Adversarial Examples for Text Classification

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Study on relationship between adversarial texts and language errors: a human-computer interaction perspective;Behaviour & Information Technology;2024-09-04