Towards a unified framework for imperceptible textual attacks

doi:10.1007/s10489-024-05292-6

	Towards a unified framework for imperceptible textual attacks
	Shi, Jiahui; Li, Linjing; Zeng, Daniel
发表期刊	APPLIED INTELLIGENCE
ISSN	0924-669X
	2024-02-09
页码	14
通讯作者	Li, Linjing(linjing.li@ia.ac.cn)
摘要	Despite the great success of Deep Neural Networks (DNNs) in the field of natural language processing (NLP), they are increasingly facing tremendous threats from textual attacks in two kinds: adversarial attacks and backdoor attacks. Both of them are able to manipulate DNNs into producing the designated target label. By searching the optimal replacement in the massive space of possible candidates, current textual attacks deal with each input sample one at a time. However, attacking in this manner is time consuming, and the generated samples suffer from low semantic consistency and language fluency. To address this issue, we design a unified framework for targeted adversarial attacks and backdoor attacks, which employs a masked language model to produce imperceptible poisoned samples directly. We conduct extensive experiments on three benchmark datasets for three different NLP model architectures. Experimental results reveal that the proposed framework can achieve the state-of-the-art attacking performance for backdoor attacks with a substantial improvement, and a more pronounced improvements for targeted adversarial attacks, while concurrently maintaining the high linguistic quality of generated samples.
关键词	Adversarial attack Backdoor attack Natural language processing Adversarial machine learning
DOI	10.1007/s10489-024-05292-6
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[XDA27030100] ; Strategic Priority Research Program of Chinese Academy of Sciences[72293573] ; Strategic Priority Research Program of Chinese Academy of Sciences[72293575] ; National Natural Science Foundation of China
项目资助者	National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Sciences ; National Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001157397800001
出版者	SPRINGER
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/55575
专题	多模态人工智能系统全国重点实验室
通讯作者	Li, Linjing
作者单位	Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Shi, Jiahui,Li, Linjing,Zeng, Daniel. Towards a unified framework for imperceptible textual attacks[J]. APPLIED INTELLIGENCE,2024:14.
APA	Shi, Jiahui,Li, Linjing,&Zeng, Daniel.(2024).Towards a unified framework for imperceptible textual attacks.APPLIED INTELLIGENCE,14.
MLA	Shi, Jiahui,et al."Towards a unified framework for imperceptible textual attacks".APPLIED INTELLIGENCE (2024):14.