{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-neural-network-architecture-combining-gated","title":"A Neural Network Architecture Combining Gated Recurrent Unit (GRU) and Support Vector Machine (SVM) for Intrusion Detection in Network Traffic Data","arxiv_id":"1709.03082","date":"2017-09-10","proceeding":null,"authors":["Abien Fred Agarap"],"abstract":"Gated Recurrent Unit (GRU) is a recently-developed variation of the long\nshort-term memory (LSTM) unit, both of which are types of recurrent neural\nnetwork (RNN). Through empirical evidence, both models have been proven to be\neffective in a wide variety of machine learning tasks such as natural language\nprocessing (Wen et al., 2015), speech recognition (Chorowski et al., 2015), and\ntext classification (Yang et al., 2016). Conventionally, like most neural\nnetworks, both of the aforementioned RNN variants employ the Softmax function\nas its final output layer for its prediction, and the cross-entropy function\nfor computing its loss. In this paper, we present an amendment to this norm by\nintroducing linear support vector machine (SVM) as the replacement for Softmax\nin the final output layer of a GRU model. Furthermore, the cross-entropy\nfunction shall be replaced with a margin-based function. While there have been\nsimilar studies (Alalshekmubarak & Smith, 2013; Tang, 2013), this proposal is\nprimarily intended for binary classification on intrusion detection using the\n2013 network traffic data from the honeypot systems of Kyoto University.\nResults show that the GRU-SVM model performs relatively higher than the\nconventional GRU-Softmax model. The proposed model reached a training accuracy\nof ~81.54% and a testing accuracy of ~84.15%, while the latter was able to\nreach a training accuracy of ~63.07% and a testing accuracy of ~70.75%. In\naddition, the juxtaposition of these two final output layers indicate that the\nSVM would outperform Softmax in prediction time - a theoretical implication\nwhich was supported by the actual training and testing time in the study.","url_abs":"http://arxiv.org/abs/1709.03082v8","url_pdf":"http://arxiv.org/pdf/1709.03082v8.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-neural-network-architecture-combining-gated","repo_url":"https://github.com/AFAgarap/gru-svm","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-neural-network-architecture-combining-gated","repo_url":"https://github.com/AFAgarap/cnn-svm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-neural-network-architecture-combining-gated","repo_url":"https://github.com/AFAgarap/malware-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"a-neural-network-architecture-combining-gated","repo_url":"https://github.com/AFAgarap/wisconsin-breast-cancer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-neural-network-architecture-combining-gated","repo_url":"https://github.com/da-moon/classifiers-monorepo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"intrusion-detection","task_name":"Intrusion Detection"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[{"method_slug":"gru","method_name":"GRU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/intrusion-detection-on-20newsgroups","task":"Intrusion Detection","dataset":"20NewsGroups","model":"intrusion detection","rank_in_archive_order":1,"of":1,"metrics":{"Actions Top-1 (S2)":"action"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.03082","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}