中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 互联网大数据与安全信息学研究中心
SHAPAttack: Shapley-Guided Multigranularity Adversarial Attack Against Text Transformers

文献类型：期刊论文

作者Shi, Jiahui; Li, Linjing; Zeng, Daniel
刊名IEEE INTELLIGENT SYSTEMS
出版日期2024-05-01
卷号39期号:3页码:45-53
关键词Perturbation methods Transformers Intelligent systems Security Task analysis Games Text categorization Text analysis Query processing Benchmark testing Adversarial machine learning Ranking (statistics)
ISSN号1541-1672
DOI10.1109/MIS.2024.3379377
通讯作者Shi, Jiahui(jiahui.shi@ia.ac.cn)
英文摘要Despite the great success of text transformers, recent studies have revealed their vulnerability to textual adversarial attacks. Existing attack methods are limited to a single granularity and often suffer from a low attack success rate and a high query cost. To mitigate these issues, we propose a Shapley-guided multigranularity adversarial attack (SHAPAttack) that generates adversarial examples (AEs). SHAPAttack expands the perturbation space by combining granularities at both the word and phrase levels, which enhances the diversity of the generated AEs. To improve attack efficiency and reduce the query cost, SHAPAttack adopts a query-free constituent importance ranking method guided by the Shapley value to measure the importance of each constituent. We conduct extensive experiments on three benchmark datasets across three text transformers. The experimental results demonstrate that SHAPAttack outperforms strong baselines in terms of both attack success rate and model queries, indicating the effectiveness and efficiency of the proposed method.
资助项目Strategic Priority Research Program of Chinese Academy of Sciences[XDA27030100] ; National Natural Science Foundation of China[72293573] ; National Natural Science Foundation of China[72293575]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001258215100006
出版者IEEE COMPUTER SOC
资助机构Strategic Priority Research Program of Chinese Academy of Sciences ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/59112]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_互联网大数据与安全信息学研究中心
舆论大数据科学与技术应用联合实验室
通讯作者Shi, Jiahui
作者单位Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Shi, Jiahui,Li, Linjing,Zeng, Daniel. SHAPAttack: Shapley-Guided Multigranularity Adversarial Attack Against Text Transformers[J]. IEEE INTELLIGENT SYSTEMS,2024,39(3):45-53.
APA Shi, Jiahui,Li, Linjing,&Zeng, Daniel.(2024).SHAPAttack: Shapley-Guided Multigranularity Adversarial Attack Against Text Transformers.IEEE INTELLIGENT SYSTEMS,39(3),45-53.
MLA Shi, Jiahui,et al."SHAPAttack: Shapley-Guided Multigranularity Adversarial Attack Against Text Transformers".IEEE INTELLIGENT SYSTEMS 39.3(2024):45-53.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。