Attention-guided transformation-invariant attack for black-box adversarial examples
文献类型:期刊论文
作者 | Zhu, Jiaqi1; Dai, Feng2; Yu, Lingyun1,3; Xie, Hongtao1; Wang, Lidong4; Wu, Bo5; Zhang, Yongdong1 |
刊名 | INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS |
出版日期 | 2022-01-11 |
页码 | 24 |
ISSN号 | 0884-8173 |
关键词 | adversarial examples attention media convergence security transformation-invariant |
DOI | 10.1002/int.22808 |
英文摘要 | With the development of media convergence, information acquisition is no longer limited to traditional media, such as newspapers and televisions, but more from digital media on the Internet, where media contents should be under supervision by platforms. At present, the media content analysis technology of Internet platforms relies on deep neural networks (DNNs). However, DNNs show vulnerability to adversarial examples, which results in security risks. Therefore, it is necessary to adequately study the internal mechanism of adversarial examples to build more effective supervision models. When coming to practical applications, supervision models are mostly faced with black-box attacks, where cross-model transferability of adversarial examples has attracted increasing attention. In this paper, to improve the transferability of adversarial examples, we propose an attention-guided transformation-invariant adversarial attack method, which incorporates an attention mechanism to disrupt the most distinctive features and simultaneously ensures adversarial attack invariance under different transformations. Specifically, we dynamically weight the latent features according to an attention mechanism and disrupt them accordingly. Meanwhile, considering the lack of semantics in low-level features, high-level semantics are introduced as spatial guidance to make low-level feature perturbations concentrate on the most discriminative regions. Moreover, since the attention heatmaps may vary significantly across different models, a transformation-invariant aggregated attack strategy is proposed to alleviate overfitting to the proxy model attention. Comprehensive experimental results show that the proposed method can significantly improve the transferability of adversarial examples. |
资助项目 | National Key Research and Development Program of China[2018YFB0804203] ; National Natural Science Foundation of China[62121002] ; National Natural Science Foundation of China[U1936210] ; National Natural Science Foundation of China[62072438] ; National Natural Science Foundation of China[U1936110] ; National Natural Science Foundation of China[62102127] ; Hefei Postdoctoral Research Activities Foundation[BSH202101] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | WILEY |
WOS记录号 | WOS:000741469300001 |
源URL | [http://119.78.100.204/handle/2XEOYT63/18295] |
专题 | 中国科学院计算技术研究所期刊论文_英文 |
通讯作者 | Xie, Hongtao |
作者单位 | 1.Univ Sci & Technol China, Sch Informat Sci & Technol, 443 Huangshan Rd, Hefei 230027, Peoples R China 2.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Beijing, Peoples R China 3.Hefei Comprehens Natl Sci Ctr, Inst Artificial Intelligence, Hefei, Peoples R China 4.Beijing Radio & TV Stn, Beijing, Peoples R China 5.MIT IBM Watson AI Lab, Cambridge, MA USA |
推荐引用方式 GB/T 7714 | Zhu, Jiaqi,Dai, Feng,Yu, Lingyun,et al. Attention-guided transformation-invariant attack for black-box adversarial examples[J]. INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS,2022:24. |
APA | Zhu, Jiaqi.,Dai, Feng.,Yu, Lingyun.,Xie, Hongtao.,Wang, Lidong.,...&Zhang, Yongdong.(2022).Attention-guided transformation-invariant attack for black-box adversarial examples.INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS,24. |
MLA | Zhu, Jiaqi,et al."Attention-guided transformation-invariant attack for black-box adversarial examples".INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS (2022):24. |
入库方式: OAI收割
来源:计算技术研究所
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。