{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T09:33:22Z","timestamp":1790674402131,"version":"4.1.0"},"reference-count":58,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"BRIDGEABLE ANR Research and Teaching Chair in AI"},{"name":"Romanian National Authority for Scientific Research and Innovation, UEFISCDI","award":["425PED\/2020, and PN-III-P2-2.1-PED-2019-2392"],"award-info":[{"award-number":["425PED\/2020, and PN-III-P2-2.1-PED-2019-2392"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2024,4,30]]},"abstract":"<jats:p>This article introduces a novel approach for building a robust Automatic Gesture Recognition system based on Surface Electromyographic (sEMG) signals, acquired at the forearm level. Our main contribution is to propose new constrained learning strategies that ensure robustness against adversarial perturbations by controlling the Lipschitz constant of the classifier. We focus on nonnegative neural networks for which accurate Lipschitz bounds can be derived, and we propose different spectral norm constraints offering robustness guarantees from a theoretical viewpoint. Experimental results on four publicly available datasets highlight that a good tradeoff in terms of accuracy and performance is achieved. We then demonstrate the robustness of our models, compared with standard trained classifiers in four scenarios, considering both white-box and black-box attacks.<\/jats:p>","DOI":"10.1145\/3635159","type":"journal-article","created":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T09:39:19Z","timestamp":1702028359000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["EMG-Based Automatic Gesture Recognition Using Lipschitz-Regularized Neural Networks"],"prefix":"10.1145","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4624-9442","authenticated-orcid":false,"given":"Ana","family":"Neac\u015fu","sequence":"first","affiliation":[{"name":"Centre de Centre de Vision Num\u00e9rique, Inria, CentraleSup\u00e9lec, France and Speech and Dialogue Laboratory, University Politehnica of Bucharest, Bucharest, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5943-8061","authenticated-orcid":false,"given":"Jean-Christophe","family":"Pesquet","sequence":"additional","affiliation":[{"name":"Centre de Centre de Vision Num\u00e9rique, Inria, CentraleSup\u00e9lec, Gif-sur-Yvette, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1710-8010","authenticated-orcid":false,"given":"Corneliu","family":"Burileanu","sequence":"additional","affiliation":[{"name":"Speech and Dialogue Laboratory, University Politehnica of Bucharest, Bucharest, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,2,22]]},"reference":[{"key":"e_1_3_3_2_2","first-page":"284","volume-title":"Proc. IEEE Int. Conf. Telecomm. Signal Porcess.","author":"Andronache Cristina","year":"2022","unstructured":"Cristina Andronache, Marian Negru, Ioana B\u0103di\u0163oiu, George Cioroiu, Ana Neacsu, and Corneliu Burileanu. 2022. Automatic gesture recognition framework based on forearm EMG activity. In Proc. IEEE Int. Conf. Telecomm. Signal Porcess.284\u2013288."},{"key":"e_1_3_3_3_2","first-page":"301","volume-title":"Proc. IEEE Int. Conf. Telecomm. Signal Porcess.","author":"Andronache Cristina","year":"2020","unstructured":"Cristina Andronache, Marian Negru, Ana Neac\u015fu, George Cioroiu, Anamaria R\u0103doi, and Corneliu Burileanu. 2020. Towards extending real-time EMG-based gesture recognition system. In Proc. IEEE Int. Conf. Telecomm. Signal Porcess.Milan, 301\u2013304."},{"key":"e_1_3_3_4_2","first-page":"291","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Anil Cem","year":"2019","unstructured":"Cem Anil, James Lucas, and Roger Grosse. 2019. Sorting out Lipschitz function approximation. In Proc. Int. Conf. Mach. Learn.Long Beach, California, 291\u2013301."},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2014.53"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2014.2328495"},{"key":"e_1_3_3_7_2","doi-asserted-by":"crossref","unstructured":"Heinz H. Bauschke and Patrick L. Combettes. 2019. Convex Analysis and Monotone Operator Theory in Hilbert Spaces. 2nd ed. Corrected Printing. New York: Springer 1 (2019) 1\u2013619.","DOI":"10.1007\/978-3-319-48311-5_31"},{"key":"e_1_3_3_8_2","first-page":"513","volume-title":"USENIX Security Symp.","author":"Carlini Nicholas","year":"2016","unstructured":"Nicholas Carlini, Pratyush Mishra, Tavish Vaidya, Yuankai Zhang, Micah Sherr, Clay Shields, David Wagner, and Wenchao Zhou. 2016. Hidden voice commands. In USENIX Security Symp.Austin, TX, 513\u2013530."},{"key":"e_1_3_3_9_2","first-page":"39","volume-title":"IEEE Symp. Security Privacy","author":"Carlini Nicholas","year":"2017","unstructured":"Nicholas Carlini and David Wagner. 2017. Towards evaluating the robustness of neural networks. In IEEE Symp. Security Privacy. San Jose, CA, 39\u201357."},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00637"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-015-0746-4"},{"key":"e_1_3_3_12_2","unstructured":"Tong Chen Jean-Bernard Lasserre Victor Magron and Edouard Pauwels. 2020. Semialgebraic optimization for Lipschitz constants of ReLU networks. In Proc. Int. Conf. Neural Info. Process. Syst. Curran Associates Inc. 12."},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-017-0705-5"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2310059"},{"key":"e_1_3_3_15_2","first-page":"854","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cisse Moustapha","year":"2017","unstructured":"Moustapha Cisse, Piotr Bojanowski, Edouard Grave, Yann Dauphin, and Nicolas Usunier. 2017. Parseval networks: Improving robustness to adversarial examples. In Proc. Int. Conf. Mach. Learn.Sydney, NSW, 854\u2013863."},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1137\/060669498"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11228-019-00526-z"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11228-010-0147-7"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1137\/19M1272780"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3069677"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1137\/050626090"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2019.2896269"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/34.546259"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3179630"},{"key":"e_1_3_3_25_2","first-page":"11423","volume-title":"Adv. Neural Info. Process. Syst.","author":"Fazlyab Mahyar","year":"2019","unstructured":"Mahyar Fazlyab, Alexander Robey, Hamed Hassani, Manfred Morari, and George Pappas. 2019. Efficient and accurate estimation of lipschitz constants for deep neural networks. In Adv. Neural Info. Process. Syst.Vancouver, Canada, 11423\u201311434."},{"key":"e_1_3_3_26_2","first-page":"8440","volume-title":"Proc. IEEE Int. Conf. Robot. Autom.","author":"Gao Xiaojie","year":"2020","unstructured":"Xiaojie Gao, Yueming Jin, Qi Dou, and Pheng-Ann Heng. 2020. Automatic gesture recognition in robot-assisted surgery with reinforcement learning and tree search. In Proc. IEEE Int. Conf. Robot. Autom.Paris, France, 8440\u20138446."},{"key":"e_1_3_3_27_2","volume-title":"Int. Conf. Learn. Represent.","author":"Geiping Jonas","year":"2020","unstructured":"Jonas Geiping, Liam H. Fowl, W. Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, and Tom Goldstein. 2020. Witches\u2019 Brew: Industrial scale data poisoning via gradient matching. In Int. Conf. Learn. Represent."},{"key":"e_1_3_3_28_2","volume-title":"Int. Conf. Learn. Represent.","author":"Goodfellow Ian J.","year":"2015","unstructured":"Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In Int. Conf. Learn. Represent.San Diego, CA."},{"key":"e_1_3_3_29_2","first-page":"8057","volume-title":"Proc. IEEE Int. Conf. Acoust. Speech Signal Process.","author":"Gupta Kavya","year":"2021","unstructured":"Kavya Gupta, Beatrice Pesquet-Popescu, Fateh Kaakai, and Jean-Christophe Pesquet. 2021. A quantitative analysis of the robustness of neural networks for tabular data. In Proc. IEEE Int. Conf. Acoust. Speech Signal Process.8057\u20138061."},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0307-0"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22155855"},{"key":"e_1_3_3_32_2","first-page":"1534","volume-title":"Proc. Int. Conf. Control Autom. Robotics & Vision","author":"Khushaba Rami N.","year":"2012","unstructured":"Rami N. Khushaba and Sarath Kodagoda. 2012. Electromyogram (EMG) feature reduction using mutual components analysis for multifunction prosthetic fingers control. In Proc. Int. Conf. Control Autom. Robotics & Vision. Guangzhou, China, 1534\u20131539."},{"key":"e_1_3_3_33_2","first-page":"30","volume-title":"Proc. Int. Conf. Intell. User Interfac.","author":"Kim Jonghwa","year":"2008","unstructured":"Jonghwa Kim, Stephan Mastnik, and Elisabeth Andr\u00e9. 2008. EMG-based hand gesture recognition for realtime biosignal interfacing. In Proc. Int. Conf. Intell. User Interfac.Canaria, Spain, 30\u201339."},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2377273"},{"key":"e_1_3_3_35_2","first-page":"2103","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recogn.","author":"Kopuklu Okan","year":"2018","unstructured":"Okan Kopuklu, Neslihan Kose, and Gerhard Rigoll. 2018. Motion fused frames: Data level fusion strategy for hand gesture recognition. In Proc. IEEE Conf. Comput. Vis. Pattern Recogn.Utah, 2103\u20132111."},{"key":"e_1_3_3_36_2","volume-title":"Int. Conf. on Learn. Represent.","author":"Kurakin Alexey","year":"2017","unstructured":"Alexey Kurakin, Ian Goodfellow, and Samy Bengio. 2017. Adversarial machine learning at scale. In Int. Conf. on Learn. Represent.Toulon, France."},{"key":"e_1_3_3_37_2","first-page":"1975","volume-title":"Proc. IEEE European Signal Processing Conf.","author":"Kurakin Alexey","year":"2012","unstructured":"Alexey Kurakin, Zhengyou Zhang, and Zicheng Liu. 2012. A real time system for dynamic hand gesture recognition with a depth sensor. In Proc. IEEE European Signal Processing Conf.Bucharest, Romania, 1975\u20131979."},{"key":"e_1_3_3_38_2","volume-title":"Int. Conf. on Learning Representations","author":"Latorre Fabian","year":"2020","unstructured":"Fabian Latorre, Paul Rolland, and Volkan Cevher. 2020. Lipschitz constant estimation of neural networks via sparse polynomial optimization. In Int. Conf. on Learning Representations."},{"key":"e_1_3_3_39_2","first-page":"7644","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recogn.","author":"Li Peiliang","year":"2019","unstructured":"Peiliang Li, Xiaozhi Chen, and Shaojie Shen. 2019. Stereo R-CNN based 3D object detection for autonomous driving. In Proc. IEEE Conf. Comput. Vis. Pattern Recogn.Long Beach, CA, 7644\u20137652."},{"key":"e_1_3_3_40_2","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards deep learning models resistant to adversarial attacks. In Proc. Int. Conf. Learn. Represent.Vancouver, BC, Canada."},{"key":"e_1_3_3_41_2","first-page":"8389","volume-title":"Proc. IEEE Int. Conf. Acoust. Speech Signal Process.","author":"Neac\u015fu Ana","year":"2020","unstructured":"Ana Neac\u015fu, Jean-Christophe Pesquet, and Corneliu Burileanu. 2020. Accuracy-robustness trade-off for positively weighted neural networks. In Proc. IEEE Int. Conf. Acoust. Speech Signal Process.Barcelona, Spain, 8389\u20138393."},{"key":"e_1_3_3_42_2","first-page":"232","volume-title":"Proc. Int. Conf. Telecommunications Signal Process.","author":"Neacsu Ana Antonia","year":"2019","unstructured":"Ana Antonia Neacsu, George Cioroiu, Anamaria R\u0103doi, and Corneliu Burileanu. 2019. Automatic EMG-based hand gesture recognition system using time-domain descriptors and fully-connected neural networks. In Proc. Int. Conf. Telecommunications Signal Process.Budapest, Hungary, 232\u2013235."},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"e_1_3_3_44_2","first-page":"1","volume-title":"IEEE Latin American Conf. Comput. Intell.","author":"Orjuela-Ca\u00f1\u00f3n Alvaro David","year":"2017","unstructured":"Alvaro David Orjuela-Ca\u00f1\u00f3n, Andr\u00e9s F. Ru\u00edz-Olaya, and Leonardo Forero. 2017. Deep neural network for EMG signal classification of wrist position: Preliminary results. In IEEE Latin American Conf. Comput. Intell.Arequipa, Peru, 1\u20135."},{"key":"e_1_3_3_45_2","volume-title":"IEEE Symp. Security Privacy","author":"Papernot Nicolas","year":"2016","unstructured":"Nicolas Papernot, Patrick McDaniel, Somesh Jha, Matt Fredrikson, Z. Berkay Celik, and Ananthram Swami. 2016. The limitations of deep learning in adversarial settings. In IEEE Symp. Security Privacy. Saarbr\u00fccken, Germany."},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3050444"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2022.911204"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0186132"},{"key":"e_1_3_3_49_2","article-title":"Intelligent human-computer interaction based on surface EMG gesture recognition","author":"Qi Jinxian","year":"2019","unstructured":"Jinxian Qi, Guozhang Jiang, Gongfa Li, Ying Sun, and Bo Tao. 2019. Intelligent human-computer interaction based on surface EMG gesture recognition. IEEE Access 7, 1 (2019), 61378\u201361387.","journal-title":"IEEE Access"},{"key":"e_1_3_3_50_2","article-title":"Searching for activation functions","author":"Ramachandran Prajit","year":"2018","unstructured":"Prajit Ramachandran, Barret Zoph, and Quoc V Le. 2018. Searching for activation functions. Proc. Int. Conf. Learn. Represent. (30 Apr.\u201303 May2018), 1\u201313.","journal-title":"Proc. Int. Conf. Learn. Represent."},{"key":"e_1_3_3_51_2","first-page":"3839","volume-title":"Proc. Ann. Conf. Neur. Inform. Proc. Syst.","author":"Scaman Kevin","year":"2018","unstructured":"Kevin Scaman and Aladin Virmaux. 2018. Lipschitz regularity of deep neural networks: Analysis and efficient estimation. In Proc. Ann. Conf. Neur. Inform. Proc. Syst.Montreal, Canada, 3839\u20133848."},{"key":"e_1_3_3_52_2","first-page":"505","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recogn.","author":"Serrurier Mathieu","year":"2021","unstructured":"Mathieu Serrurier, Franck Mamalet, Alberto Gonz\u00e1lez-Sanz, Thibaut Boissin, Jean-Michel Loubes, and Eustasio del Barrio. 2021. Achieving robustness in classification using optimal transport with hinge regularization. In Proc. IEEE Conf. Comput. Vis. Pattern Recogn.Nashville, 505\u2013514."},{"key":"e_1_3_3_53_2","volume-title":"Int. Conf. Learn. Represent.","author":"Szegedy Christian","year":"2014","unstructured":"Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2014. Intriguing properties of neural networks. In Int. Conf. Learn. Represent.Banff, Canada."},{"key":"e_1_3_3_54_2","volume-title":"Int. Conf. Learn. Represent.","author":"Takeru Miyato","year":"2018","unstructured":"Miyato Takeru, Kataoka Toshiki, Koyama Masanori, and Yoshida Yuichi. 2018. Spectral normalization for generative adversarial networks. In Int. Conf. Learn. Represent.Vancouver, Canada."},{"key":"e_1_3_3_55_2","unstructured":"Dimitris Tsipras Shibani Santurkar Logan Engstrom Alexander Turner and Aleksander Madry. 2019. Robustness may be at odds with accuracy. Int. Conf. Learn. Represent. (2019) 1\u201320."},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23135775"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202000261"},{"key":"e_1_3_3_58_2","volume-title":"IOP Conf. Mater. Sci. Eng.","author":"Widiastuti Nelly Indriani","year":"2019","unstructured":"Nelly Indriani Widiastuti. 2019. Convolution neural network for text mining and natural language processing. In IOP Conf. Mater. Sci. Eng., Vol. 662. Kazimierz Dolny, Poland."},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2021.779353"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3635159","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3635159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:06Z","timestamp":1750286946000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3635159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,22]]},"references-count":58,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4,30]]}},"alternative-id":["10.1145\/3635159"],"URL":"https:\/\/doi.org\/10.1145\/3635159","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,22]]},"assertion":[{"value":"2023-05-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-20","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}