{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:21:32Z","timestamp":1750220492656,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T00:00:00Z","timestamp":1634256000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of Tianjin","award":["No. 18ZXZNGX00200"],"award-info":[{"award-number":["No. 18ZXZNGX00200"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,15]]},"DOI":"10.1145\/3497623.3497674","type":"proceedings-article","created":{"date-parts":[[2022,2,5]],"date-time":"2022-02-05T00:30:14Z","timestamp":1644021014000},"page":"314-321","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-paths Deep Convolutional Neural Network Based on Knowledge Distillation"],"prefix":"10.1145","author":[{"given":"Yi","family":"Lin","sequence":"first","affiliation":[{"name":"School of Computer Science, Nankai University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Cyber Science, Nankai University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Cyber Science, Nankai University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Namin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nankai University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Cyber Science, Nankai University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,2,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Simonyan A.","year":"2014","unstructured":"K. Simonyan and A. Zisserman . \u201c Very deep convolutional networks for large-scale image recognition[J] ,\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , 2014 . K. Simonyan and A. Zisserman. \u201cVery deep convolutional networks for large-scale image recognition[J],\u201d in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014."},{"key":"e_1_3_2_1_6_1","volume-title":"Computer Science","author":"Goodfellow I J","year":"2014","unstructured":"Goodfellow I J , Shlens J , and Szegedy C . \u201c Explaining and Harnessing Adversarial Examples[J] .\u201d Computer Science , 2014 . Goodfellow I J, Shlens J, and Szegedy C. \u201cExplaining and Harnessing Adversarial Examples[J].\u201d Computer Science, 2014."},{"key":"e_1_3_2_1_7_1","volume-title":"Robustness of classifiers: from adversarial to random noise[J]","author":"Fawzi A","year":"2016","unstructured":"Fawzi A , Moosavi-Dezfooli S M , and Frossard P . \u201c Robustness of classifiers: from adversarial to random noise[J] .\u201d 2016 . Fawzi A, Moosavi-Dezfooli S M, and Frossard P. \u201cRobustness of classifiers: from adversarial to random noise[J].\u201d 2016."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00093"},{"key":"e_1_3_2_1_9_1","volume-title":"ICPR","author":"Yi L","year":"2020","unstructured":"Yi L , Namin W , Xiaoqing M , \u201c How Does DCNN Make Decisions? [C] \u201d. ICPR , 2020 . Yi L, Namin W, Xiaoqing M, \u201cHow Does DCNN Make Decisions? [C]\u201d. ICPR, 2020."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"e_1_3_2_1_11_1","volume-title":"Efficient Adversarial Training with Transferable Adversarial Examples[J]","author":"Zheng H","year":"2019","unstructured":"Zheng H , Zhang Z , Gu J , \u201c Efficient Adversarial Training with Transferable Adversarial Examples[J] .\u201d 2019 . Zheng H, Zhang Z, Gu J, \u201cEfficient Adversarial Training with Transferable Adversarial Examples[J].\u201d 2019."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00034"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00103"},{"key":"e_1_3_2_1_14_1","volume-title":"MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks[J]","author":"Srisakaokul S","year":"2018","unstructured":"Srisakaokul S , Zhong Z , Zhang Y , \u201c MULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks[J] .\u201d 2018 . Srisakaokul S, Zhong Z, Zhang Y, \u201cMULDEF: Multi-model-based Defense Against Adversarial Examples for Neural Networks[J].\u201d 2018."},{"key":"e_1_3_2_1_15_1","volume-title":"A study of the effect of JPG compression on adversarial images[J]","author":"Dziugaite Z.","year":"2016","unstructured":"G. K. Dziugaite , Z. Ghahramani , and D. M. Roy , \u201c A study of the effect of JPG compression on adversarial images[J] .\u201d 2016 . G. K. Dziugaite, Z. Ghahramani, and D. M. Roy, \u201cA study of the effect of JPG compression on adversarial images[J].\u201d 2016."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.153"},{"key":"e_1_3_2_1_17_1","volume-title":"DNDNet: Reconfiguring CNN for Adversarial Robustness[C]","author":"Goel A","year":"2020","unstructured":"Goel A , Agarwal A , Vatsa M , \u201c DNDNet: Reconfiguring CNN for Adversarial Robustness[C] .\u201d IEEE , 2020 . Goel A, Agarwal A, Vatsa M, \u201cDNDNet: Reconfiguring CNN for Adversarial Robustness[C].\u201d IEEE, 2020."},{"key":"e_1_3_2_1_18_1","volume-title":"Improving Image Classification Robustness through Selective CNN-Filters Fine-Tuning","author":"Bianchi A","year":"2019","unstructured":"Bianchi A , Vendra M R , Protopapas P , \u201c Improving Image Classification Robustness through Selective CNN-Filters Fine-Tuning .\u201d 2019 . Bianchi A, Vendra M R, Protopapas P, \u201cImproving Image Classification Robustness through Selective CNN-Filters Fine-Tuning.\u201d 2019."},{"key":"e_1_3_2_1_19_1","volume-title":"When NAS Meets Robustness: In Search of Robust Architectures Against Adversarial Attacks[J]","author":"Guo M","year":"2019","unstructured":"Guo M , Yang Y , R Xu , \u201c When NAS Meets Robustness: In Search of Robust Architectures Against Adversarial Attacks[J] .\u201d 2019 . Guo M, Yang Y, R Xu, \u201cWhen NAS Meets Robustness: In Search of Robust Architectures Against Adversarial Attacks[J].\u201d 2019."},{"key":"e_1_3_2_1_20_1","volume-title":"Computer Science","author":"Gu L.","year":"2015","unstructured":"S. Gu , and L. Rigazio , \u201c Towards Deep Neural Network Architectures Robust to Adversarial Examples[J] .\u201d Computer Science , 2015 . S. Gu, and L. Rigazio, \u201cTowards Deep Neural Network Architectures Robust to Adversarial Examples[J].\u201d Computer Science, 2015."},{"key":"e_1_3_2_1_21_1","volume-title":"Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients[J]","author":"Ross F.","year":"2017","unstructured":"A. S. Ross , and F. Doshi-Velez , \u201c Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients[J] \u201d, 2017 . A. S. Ross, and F. Doshi-Velez, \u201cImproving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients[J]\u201d, 2017."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"e_1_3_2_1_23_1","volume-title":"Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser[J]","author":"Liao F","year":"2017","unstructured":"Liao F , Liang M , Dong Y , \u201c Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser[J] .\u201d 2017 . Liao F, Liang M, Dong Y, \u201cDefense against Adversarial Attacks Using High-Level Representation Guided Denoiser[J].\u201d 2017."},{"key":"e_1_3_2_1_24_1","volume-title":"SafetyNet: Detecting and Rejecting Adversarial Examples Robustly[J]","author":"Lu J","year":"2017","unstructured":"Lu J , Issaranon T , and Forsyth D . \u201c SafetyNet: Detecting and Rejecting Adversarial Examples Robustly[J] \u201d. IEEE Computer Society , 2017 . Lu J, Issaranon T, and Forsyth D. \u201cSafetyNet: Detecting and Rejecting Adversarial Examples Robustly[J]\u201d. IEEE Computer Society, 2017."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00357"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Meng D and Chen H. \u201cMagNet: a Two-Pronged Defense against Adversarial Examples[J]\u201d. 2017.  Meng D and Chen H. \u201cMagNet: a Two-Pronged Defense against Adversarial Examples[J]\u201d. 2017.","DOI":"10.1145\/3133956.3134057"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CISP-BMEI48845.2019.8966074"},{"issue":"7","key":"e_1_3_2_1_28_1","first-page":"38","article-title":"Distilling the knowledge in a neural network[J]","volume":"14","author":"Hinton O.","year":"2015","unstructured":"G. Hinton , O. Vinyals , and J. Dean , \u201c Distilling the knowledge in a neural network[J] \u201d, Computer Science , 2015 , 14 ( 7 ): 38 - 39 . G. Hinton, O. Vinyals, and J. Dean, \u201cDistilling the knowledge in a neural network[J]\u201d, Computer Science, 2015, 14(7):38-39.","journal-title":"Computer Science"},{"key":"e_1_3_2_1_29_1","article-title":"One pixel attack for fooling deep neural networks[J]","author":"Su J","year":"2017","unstructured":"Su J , Vargas D V , Kouichi S. \u201c One pixel attack for fooling deep neural networks[J] .\u201d IEEE Transactions on Evolutionary Computation , 2017 . Su J, Vargas D V, Kouichi S. \u201cOne pixel attack for fooling deep neural networks[J].\u201d IEEE Transactions on Evolutionary Computation, 2017.","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_33_1","article-title":"Squeeze-and-Excitation Networks[J]","volume":"2017","author":"Jie H","unstructured":"Jie H , Li S , Gang S , \u201c Squeeze-and-Excitation Networks[J] \u201d . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , PP (99). Jie H, Li S, Gang S, \u201cSqueeze-and-Excitation Networks[J]\u201d. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, PP (99).","journal-title":". IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Learning Representations","author":"Kingma J.","year":"2014","unstructured":"D. Kingma , and J. Ba . \u201c Adam: a method for stochastic optimization[J] \u201d. in International Conference on Learning Representations , 2014 . D. Kingma, and J. Ba. \u201cAdam: a method for stochastic optimization[J]\u201d. in International Conference on Learning Representations, 2014."}],"event":{"name":"ICCPR '21: 2021 10th International Conference on Computing and Pattern Recognition","acronym":"ICCPR '21","location":"Shanghai China"},"container-title":["2021 10th International Conference on Computing and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3497623.3497674","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3497623.3497674","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:24Z","timestamp":1750193364000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3497623.3497674"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,15]]},"references-count":34,"alternative-id":["10.1145\/3497623.3497674","10.1145\/3497623"],"URL":"https:\/\/doi.org\/10.1145\/3497623.3497674","relation":{},"subject":[],"published":{"date-parts":[[2021,10,15]]},"assertion":[{"value":"2022-02-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}