{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:36:35Z","timestamp":1777703795381,"version":"3.51.4"},"reference-count":27,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2019,7,2]],"date-time":"2019-07-02T00:00:00Z","timestamp":1562025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2019,10,25]]},"abstract":"<jats:p>\n                    Deep Neural Network is an application of Big Data, and the robustness of Big Data is one of the most important issues. This paper proposes a new approach named PCD for computing adversarial examples for Deep Neural Network (DNN) and increase the robustness of Big Data. In safety-critical applications, adversarial examples are big threats to the reliability of DNNs. PCD generates adversarial examples by generating different coverage of pooling functions using gradient ascent. Among the 2707 input images, PCD generates 672 adversarial examples with\n                    <jats:italic>L<\/jats:italic>\n                    <jats:sub>\u221e<\/jats:sub>\n                    distances less than 0.3. Comparing to PGD (state-of-art tool for generating adversarial examples with distances less than 0.3), PCD finds 1.5 times more adversarial examples than PGD (449) does.\n                  <\/jats:p>","DOI":"10.3233\/jifs-179295","type":"journal-article","created":{"date-parts":[[2019,7,2]],"date-time":"2019-07-02T10:42:43Z","timestamp":1562064163000},"page":"4615-4620","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Generating adversarial examples for DNN using pooling layers"],"prefix":"10.1177","volume":"37","author":[{"given":"Yueling","family":"Zhang","sequence":"first","affiliation":[{"name":"Computer Science and Software Engineering Institute, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geguang","family":"Pu","sequence":"additional","affiliation":[{"name":"Computer Science and Software Engineering Institute, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Computer Science and Software Engineering Institute, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Y","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Princeton University, Princeton, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2019,7,2]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2756440"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"issue":"12","key":"e_1_3_1_4_2","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He K.","year":"2016","unstructured":"HeK., ZhangX. and RenS., Deep residual learning for image recognition, CVPR (12) (2016), 770\u2013778.","journal-title":"CVPR"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2528162"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"e_1_3_1_8_2","first-page":"303","article-title":"DeepTest: Automated testing of deep-neural-network-driven autonomous cars","author":"Tian Y.","year":"2018","unstructured":"TianY., PeiK. and JanaS., DeepTest: Automated testing of deep-neural-network-driven autonomous cars, ICSE (2018), 303\u2013314.","journal-title":"ICSE"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"e_1_3_1_10_2","article-title":"DeepRoad: GAN-based Metamorphic Autonomo Driving System Testing","author":"Zhang M.","year":"2018","unstructured":"ZhangM., ZhangY. and ZhangL., DeepRoad: GAN-based Metamorphic Autonomo Driving System Testing, arXiv preprint arXiv: 1802.02295 (2018).","journal-title":"arXiv preprint arXiv: 1802.02295"},{"key":"e_1_3_1_11_2","first-page":"399","article-title":"MtNet: A multi-task neural network for dynamic malware classification","author":"Huang W.","year":"2018","unstructured":"HuangW. and StokesJ.W., MtNet: A multi-task neural network for dynamic malware classification, DIMVA (2018), 399\u2013418.","journal-title":"DIMVA"},{"key":"e_1_3_1_12_2","first-page":"577","article-title":"Malware detection with deep neural network using process behavior","volume":"2","author":"Tobiyama S.","year":"2016","unstructured":"TobiyamaS., YamaguchiY. and ShimadaH., Malware detection with deep neural network using process behavior, COMPSAC 2 (2016), 577\u2013582.","journal-title":"COMPSAC"},{"key":"e_1_3_1_13_2","first-page":"702","article-title":"Hadm: Hybrid analysis for detection of malware, IntelliSys","author":"Xu L.","year":"2016","unstructured":"XuL., ZhangD. and JayasenaN., Hadm: Hybrid analysis for detection of malware, IntelliSys, IEEE (2016), 702\u2013724.","journal-title":"IEEE"},{"key":"e_1_3_1_14_2","first-page":"91","article-title":"DeepAPT: Nation-state APT attribution using end-to-end deep neural networks","author":"Rosenberg I.","year":"2017","unstructured":"RosenbergI., SicardG. and DavidE.O., DeepAPT: Nation-state APT attribution using end-to-end deep neural networks, ICANN (2017), 91\u201399.","journal-title":"ICANN"},{"key":"e_1_3_1_15_2","first-page":"1","article-title":"Adversarial-Playground: A visualization suite showing how adversarial ex- amples fool deep learning","author":"Norton A.P.","year":"2017","unstructured":"NortonA.P. and QiY., Adversarial-Playground: A visualization suite showing how adversarial ex- amples fool deep learning, VizSec, IEEE (2017), 1\u20134.","journal-title":"VizSec, IEEE"},{"key":"e_1_3_1_16_2","first-page":"98","article-title":"Detecting cyber-physical threats in an au- tonomous robotic vehicle using Bayesian Networks","author":"Bezemskij A.","year":"2017","unstructured":"BezemskijA., LoukasG., GanD., et al., Detecting cyber-physical threats in an au- tonomous robotic vehicle using Bayesian Networks, iThings, IEEE (2017), 98\u2013103.","journal-title":"iThings, IEEE"},{"key":"e_1_3_1_17_2","article-title":"Reachability analysis of deep neural networks with provable guarantees","author":"Ruan W.","year":"2018","unstructured":"RuanW., HuangX. and KwiatkowskaM., Reachability analysis of deep neural networks with provable guarantees, arXiv preprint arXiv:1805.02242 (2018).","journal-title":"arXiv preprint arXiv:1805.02242"},{"issue":"5","key":"e_1_3_1_18_2","first-page":"39","article-title":"Towards evaluating the robustness of neural networks","author":"Carlini N.","year":"2017","unstructured":"CarliniN. and WagnerD., Towards evaluating the robustness of neural networks, IEEE Symposium on Security and Privacy (5) (2017), 39\u201357.","journal-title":"IEEE Symposium on Security and Privacy"},{"key":"e_1_3_1_19_2","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2018","unstructured":"Madry, Aleksander, MakelovAleksandar and SchmidtLudwig, Towards deep learning models resistant to adversarial attacks, ICLR (2018).","journal-title":"ICLR"},{"key":"e_1_3_1_20_2","article-title":"Developing bug-free machine learning systems with formal mathematics","author":"Selsam D.","year":"2017","unstructured":"SelsamD., LiangP. and DillD.L., Developing bug-free machine learning systems with formal mathematics, arXiv preprint arXiv:1706.08605 (2017).","journal-title":"arXiv preprint arXiv:1706.08605"},{"key":"e_1_3_1_21_2","first-page":"97","article-title":"Reluplex: An efficient SMT solver for verifying deep neural networks","author":"Katz G.","year":"2017","unstructured":"KatzG., BarrettC. and DillD.L., Reluplex: An efficient SMT solver for verifying deep neural networks, CAV pp. 97\u2013117 (2017).","journal-title":"CAV"},{"key":"e_1_3_1_22_2","article-title":"Adversarial examples that fool both human and computer vision","author":"Elsayed G.F.","year":"2018","unstructured":"ElsayedG.F., ShankarS. and CheungB., Adversarial examples that fool both human and computer vision, arXiv preprint arXiv:1802.08195 (2018).","journal-title":"arXiv preprint arXiv:1802.08195"},{"key":"e_1_3_1_23_2","article-title":"He, Spatially transformed adversarial examples","author":"Xiao C.","year":"2018","unstructured":"XiaoC., ZhuJ.Y. and LiB., He, Spatially transformed adversarial examples, arXiv preprint arXiv:1801.02612 (2018).","journal-title":"arXiv preprint arXiv:1801.02612"},{"key":"e_1_3_1_24_2","first-page":"1","article-title":"Deepxplore: Automated whitebox testing of deep learning systems","author":"Pei K.","year":"2017","unstructured":"PeiK., CaoY., YangJ. and JanaS., Deepxplore: Automated whitebox testing of deep learning systems, Symposium on Operating Systems Principles (2017), 1\u201318.","journal-title":"Symposium on Operating Systems Principles"},{"key":"e_1_3_1_25_2","article-title":"Coverage-Guided Fuzzing for Deep Neural Networks","author":"Xie X.","year":"2018","unstructured":"XieX. and MaL., Coverage-Guided Fuzzing for Deep Neural Networks, arXiv preprint arXiv:1809.01266 (2018).","journal-title":"arXiv preprint arXiv:1809.01266"},{"key":"e_1_3_1_26_2","article-title":"Whitehouse, Formal Security Analysis of Neural Networks using Symbolic Intervals","author":"Wang S.","year":"2018","unstructured":"WangS. and PeiK., Whitehouse, Formal Security Analysis of Neural Networks using Symbolic Intervals, arXiv preprint arXiv:1804.10829 (2018).","journal-title":"arXiv preprint arXiv:1804.10829"},{"key":"e_1_3_1_27_2","article-title":"Concolic Testing for Deep Neural Networks","author":"Sun Y.","year":"2018","unstructured":"SunY., WuM. and RuanW., Concolic Testing for Deep Neural Networks, arXiv preprint arXiv:1805.00089 (2018).","journal-title":"arXiv preprint arXiv:1805.00089"},{"key":"e_1_3_1_28_2","article-title":"Testing deep neural networks","author":"Sun Y.","year":"2018","unstructured":"SunY., HuangX. and KroeningD., Testing deep neural networks, arXiv preprint arXiv:1803.04792 (2018).","journal-title":"arXiv preprint arXiv:1803.04792"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-179295","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-179295","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-179295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:39:37Z","timestamp":1777455577000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-179295"}},"subtitle":[],"editor":[{"given":"Valentina E.","family":"Balas","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Jer Lang","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Jason","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Tsung-Chih","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2019,7,2]]},"references-count":27,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,10,25]]}},"alternative-id":["10.3233\/JIFS-179295"],"URL":"https:\/\/doi.org\/10.3233\/jifs-179295","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,2]]}}}