{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T06:27:48Z","timestamp":1762928868404,"version":"3.41.2"},"reference-count":23,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T00:00:00Z","timestamp":1614038400000},"content-version":"vor","delay-in-days":53,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2011845","1912753","1829674","1704287"],"award-info":[{"award-number":["2011845","1912753","1829674","1704287"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Wireless Communications and Mobile Computing"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>In recent years, a series of researches have revealed that the Deep Neural Network (DNN) is vulnerable to adversarial attack, and a number of attack methods have been proposed. Among those methods, an extremely sly type of attack named the one\u2010pixel attack can mislead DNNs to misclassify an image via only modifying one pixel of the image, leading to severe security threats to DNN\u2010based information systems. Currently, no method can really detect the one\u2010pixel attack, for which the blank will be filled by this paper. This paper proposes two detection methods, including trigger detection and candidate detection. The trigger detection method analyzes the vulnerability of DNN models and gives the most suspected pixel that is modified by the one\u2010pixel attack. The candidate detection method identifies a set of most suspected pixels using a differential evolution\u2010based heuristic algorithm. The real\u2010data experiments show that the trigger detection method has a detection success rate of 9.1%, and the candidate detection method achieves a detection success rate of 30.1%, which can validate the effectiveness of our methods.<\/jats:p>","DOI":"10.1155\/2021\/8891204","type":"journal-article","created":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T23:20:21Z","timestamp":1614122421000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Detection Mechanisms of One\u2010Pixel Attack"],"prefix":"10.1155","volume":"2021","author":[{"given":"Peng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6017-975X","authenticated-orcid":false,"given":"Zhipeng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donghyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,2,23]]},"reference":[{"key":"e_1_2_10_1_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_10_2_2","unstructured":"SocherR. LinC. C. ManningC. andNgA. Y. Parsing natural scenes and natural language with recursive neural networks Proceedings of the 28th international conference on machine learning (ICML-11) 2011 Bellevue Washington USA 129\u2013136."},{"volume-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","year":"2017","author":"Kendall A.","key":"e_1_2_10_3_2"},{"key":"e_1_2_10_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2475625"},{"key":"e_1_2_10_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701245"},{"key":"e_1_2_10_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1700349"},{"key":"e_1_2_10_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2016.2613521"},{"volume-title":"The Nature of Statistical Learning Theory","year":"2013","author":"Vapnik V.","key":"e_1_2_10_8_2"},{"key":"e_1_2_10_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0026666"},{"key":"e_1_2_10_10_2","doi-asserted-by":"crossref","unstructured":"PapernotN. McDanielP. JhaS. FredriksonM. CelikZ. B. andSwamiA. The limitations of deep learning in adversarial settings 2016 IEEE European Symposium on Security and Privacy (EuroS&P) March 2016 Saarbrucken Germany 372\u2013387 https:\/\/doi.org\/10.1109\/EuroSP.2016.36 2-s2.0-84978047763.","DOI":"10.1109\/EuroSP.2016.36"},{"key":"e_1_2_10_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"e_1_2_10_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2911697"},{"key":"e_1_2_10_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3032352"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"XiongZ. LiW. HanQ. andCaiZ. Privacy-preserving auto-driving: a GAN-based approach to protect vehicular camera data 2019 IEEE International Conference on Data Mining (ICDM) November 2019 Beijing China 668\u2013677 https:\/\/doi.org\/10.1109\/ICDM.2019.00077.","DOI":"10.1109\/ICDM.2019.00077"},{"key":"e_1_2_10_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2019.2890858"},{"key":"e_1_2_10_16_2","doi-asserted-by":"crossref","unstructured":"WangB. YaoY. ShanS. LiH. ViswanathB. ZhengH. andZhaoB. Y. Neural cleanse: identifying and mitigating backdoor attacks in neural networks 2019 IEEE Symposium on Security and Privacy (SP) May 2019 San Francisco CA USA 707\u2013723 https:\/\/doi.org\/10.1109\/SP.2019.00031 2-s2.0-85072920050.","DOI":"10.1109\/SP.2019.00031"},{"key":"e_1_2_10_17_2","doi-asserted-by":"crossref","unstructured":"NguyenA. YosinskiJ. andCluneJ. Deep neural networks are easily fooled: high confidence predictions for unrecognizable images Proceedings of the IEEE conference on computer vision and pattern recognition 2015 Boston MA USA 427\u2013436.","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"e_1_2_10_18_2","doi-asserted-by":"crossref","unstructured":"Moosavi-DezfooliS.-M. FawziA. andFrossardP. Deepfool: a simple and accurate method to fool deep neural networks Proceedings of the IEEE conference on computer vision and pattern recognition 2016 Las Vegas NV USA 2574\u20132582.","DOI":"10.1109\/CVPR.2016.282"},{"key":"e_1_2_10_19_2","doi-asserted-by":"crossref","unstructured":"NarodytskaN.andKasiviswanathanS. Simple black-box adversarial attacks on deep neural networks 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2017 Honolulu HI USA 1310\u20131318.","DOI":"10.1109\/CVPRW.2017.172"},{"key":"e_1_2_10_20_2","doi-asserted-by":"crossref","unstructured":"PapernotN. McDanielP. GoodfellowI. JhaS. CelikZ. B. andSwamiA. Practical black-box attacks against machine learning Proceedings of the 2017 ACM on Asia conference on computer and communications security April 2017 Abu Dhabi United Arab Emirates 506\u2013519 https:\/\/doi.org\/10.1145\/3052973.3053009 2-s2.0-85021992078.","DOI":"10.1145\/3052973.3053009"},{"key":"e_1_2_10_21_2","doi-asserted-by":"crossref","unstructured":"GaoJ. LanchantinJ. SoffaM. L. andQiY. Black-box generation of adversarial text sequences to evade deep learning classifiers 2018 IEEE Security and Privacy Workshops (SPW) May 2018 San Francisco CA USA 50\u201356 https:\/\/doi.org\/10.1109\/SPW.2018.00016 2-s2.0-85052223531.","DOI":"10.1109\/SPW.2018.00016"},{"key":"e_1_2_10_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-25465-X_7"},{"key":"e_1_2_10_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876179"}],"container-title":["Wireless Communications and Mobile Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2021\/8891204.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/wcmc\/2021\/8891204.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/8891204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T11:28:27Z","timestamp":1723030107000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/8891204"}},"subtitle":[],"editor":[{"given":"Wenzhong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":23,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/8891204"],"URL":"https:\/\/doi.org\/10.1155\/2021\/8891204","archive":["Portico"],"relation":{},"ISSN":["1530-8669","1530-8677"],"issn-type":[{"type":"print","value":"1530-8669"},{"type":"electronic","value":"1530-8677"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2020-09-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8891204"}}