{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:35:52Z","timestamp":1740148552128,"version":"3.37.3"},"reference-count":35,"publisher":"Wiley","license":[{"start":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T00:00:00Z","timestamp":1647820800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Collaborative Innovation Major Project of Zhengzhou","award":["20XTZX06013","61972092","61932014"],"award-info":[{"award-number":["20XTZX06013","61972092","61932014"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["20XTZX06013","61972092","61932014"],"award-info":[{"award-number":["20XTZX06013","61972092","61932014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Sensors"],"published-print":{"date-parts":[[2022,3,21]]},"abstract":"<jats:p>Deep neural networks-based image classification systems could suffer from adversarial attack algorithms, which generate input examples by adding deliberately crafted yet imperceptible noise to original inputs. To reduce the impact on human visual sense and to ensure adversarial attack ability, the input image needs to be modified by pixels in considerable iterations which is time consuming. By using sparse mapping network to map the input into a higher dimensional space, searching space of adversarial perturbation distribution is enlarged to better acquire perturbation information. Taking both searching speed and searching effectiveness into consideration, sparsity limitation is introduced to suppress unnecessary neurons during parameter updating process. Based on different eye sensitivity of different colors, maps of each color channel are disturbed by perturbations with different strengths to reduce visual perception. Numerical experiments confirm that compared with the state-of-the-art adversarial attack algorithms, the proposed SparseAdv performs a relatively high attack ability, better imperceptible visualization, and faster generation speed.<\/jats:p>","DOI":"10.1155\/2022\/4031440","type":"journal-article","created":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T01:05:14Z","timestamp":1647911114000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["A Sparsity-Limitation-Based High-Dimensional Distribution Searching Algorithm for Adversarial Attack"],"prefix":"10.1155","volume":"2022","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5520-7744","authenticated-orcid":true,"given":"Chenxi","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2081-156X","authenticated-orcid":true,"given":"Haobo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8731-2474","authenticated-orcid":true,"given":"Yan","family":"Zhuang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4974-6116","authenticated-orcid":true,"given":"Jie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450000, China"},{"name":"Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai 200240, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1170-4340","authenticated-orcid":true,"given":"Yangjie","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou 450000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1080\/01431160600746456"},{"key":"2","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"A. Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"first-page":"1026","article-title":"Delving deep into rectifiers: surpassing human-level performance on ImageNet classification","author":"K. He","key":"3"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"first-page":"5419","article-title":"Event-based vision meets deep learning on steering prediction for self-driving cars","author":"A. I. Maqueda","key":"6"},{"author":"I. J. Goodfellow","key":"7","article-title":"Explaining and harnessing adversarial examples"},{"author":"C. Szegedy","key":"8","article-title":"Intriguing properties of neural networks"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"author":"C. Xiao","key":"10","article-title":"Generating adversarial examples with adversarial networks"},{"first-page":"742","article-title":"AutoZoom: autoencoder-based zeroth order optimization method for attacking black-box neural networks","author":"C.-C. Tu","key":"11"},{"author":"A. Kurakin","key":"12","article-title":"Adversarial machine learning at scale"},{"author":"A. Madry","key":"13","article-title":"Towards deep learning models resistant to adversarial attacks"},{"first-page":"9185","article-title":"Boosting adversarial attacks with momentum","author":"Y. Dong","key":"14"},{"first-page":"2730","article-title":"Improving transferability of adversarial examples with input diversity","author":"C. Xie","key":"15"},{"first-page":"4312","article-title":"Evading defenses to transferable adversarial examples by translation-invariant attacks","author":"Y. Dong","key":"16"},{"author":"Z. Huang","key":"17","article-title":"Black-box adversarial attack with transferable model-based embedding"},{"issue":"1","key":"18","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"D. Wierstra","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"article-title":"AdvGAN++: harnessing latent layers for adversary generation","author":"S. Jandial","key":"19","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW.2019.00257"},{"first-page":"11234","article-title":"Rob-GAN: generator, discriminator, and adversarial attacker","author":"X. Liu","key":"20"},{"author":"Z. Zhao","key":"21","article-title":"Generating natural adversarial examples"},{"article-title":"AdvFaces: Adversarial face synthesis","author":"D. Deb","key":"22","doi-asserted-by":"crossref","DOI":"10.1109\/IJCB48548.2020.9304898"},{"key":"23","article-title":"The numerics of GANs","volume":"30","author":"L. Mescheder","year":"2017","journal-title":"In Advances in Neural Information Processing Systems"},{"first-page":"1151","article-title":"ColorFool: semantic adversarial colorization","author":"A. S. Shamsabadi","key":"24"},{"author":"A. Bhattad","key":"25","article-title":"Unrestricted adversarial examples via semantic manipulation"},{"first-page":"12895","article-title":"Robust superpixel-guided attentional adversarial attack","author":"X. Dong","key":"26"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.1983.0091"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1016\/0042-6989(89)90178-8"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"first-page":"770","article-title":"Deep residual learning for image recognition","author":"K. He","key":"30"},{"author":"K. Simonyan","key":"31","article-title":"Very deep convolutional networks for large-scale image recognition"},{"first-page":"1","article-title":"Going deeper with convolutions","author":"C. Szegedy","key":"32"},{"first-page":"4510","article-title":"MobileNetV2: inverted residuals and linear bottlenecks","author":"M. Sandler","key":"33"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"first-page":"4700","article-title":"Densely connected convolutional networks","author":"G. Huang","key":"35"}],"container-title":["Journal of Sensors"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2022\/4031440.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2022\/4031440.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2022\/4031440.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T01:05:21Z","timestamp":1647911121000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/js\/2022\/4031440\/"}},"subtitle":[],"editor":[{"given":"Min","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2022,3,21]]},"references-count":35,"alternative-id":["4031440","4031440"],"URL":"https:\/\/doi.org\/10.1155\/2022\/4031440","relation":{},"ISSN":["1687-7268","1687-725X"],"issn-type":[{"type":"electronic","value":"1687-7268"},{"type":"print","value":"1687-725X"}],"subject":[],"published":{"date-parts":[[2022,3,21]]}}}