Fraud's Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process

doi:10.1109/TKDE.2024.3349708

	Fraud's Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process
	Mingze Ni 1; Zhensu Sun2 ; Wei Liu 1
	2024
发表期刊	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (IF:8.9[JCR-2023],8.8[5-Year])
ISSN	2326-3865
EISSN	1558-2191
卷号	PP 期号:99 页码:3062-3075
发表状态	已发表
DOI	10.1109/TKDE.2024.3349708
摘要	Recent research has revealed that natural language processing (NLP) models are vulnerable to adversarial examples. However, the current techniques for generating such examples rely on deterministic heuristic rules, which fail to produce optimal adversarial examples. In response, this study proposes a new method called the Fraud's Bargain Attack (FBA), which uses a randomization mechanism to expand the search space and produce high-quality adversarial examples with a higher probability of success. FBA uses the Metropolis-Hasting sampler, a type of Markov Chain Monte Carlo sampler, to improve the selection of adversarial examples from all candidates generated by a customized stochastic process called the Word Manipulation Process (WMP). The WMP method modifies individual words in a contextually-aware manner through insertion, removal, or substitution. Through extensive experiments, this study demonstrates that FBA outperforms other methods in terms of attack success rate, imperceptibility and sentence quality.
关键词	Adversarial learning evasion attacks natural language processing
URL	查看原文
收录类别	EI
语种	英语
出版者	IEEE Computer Society
EI入藏号	20240315389504
EI主题词	Semantics
EI分类号	723.2 Data Processing and Image Processing ; 731.1 Control Systems ; 921.5 Optimization Techniques ; 922 Statistical Methods ; 922.2 Mathematical Statistics ; 961 Systems Science ; 971 Social Sciences
原始文献类型	Journal article (JA)
来源库	IEEE
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/354968
专题	信息科学与技术学院信息科学与技术学院_PI研究组_宋富组
作者单位	1.School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia 2.School of Information Science and Technology, ShanghaiTech University, Shanghai, China
推荐引用方式 GB/T 7714	Mingze Ni,Zhensu Sun,Wei Liu. Fraud's Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2024,PP(99):3062-3075.
APA	Mingze Ni,Zhensu Sun,&Wei Liu.(2024).Fraud's Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,PP(99),3062-3075.
MLA	Mingze Ni,et al."Fraud's Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING PP.99(2024):3062-3075.