2024-03-28T21:57:45Zhttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_oaipmhoai:ipsj.ixsq.nii.ac.jp:001921402023-11-14T00:51:14Z06164:06165:06462:09599
Lightweight Classification of IoT Malware Based on Image Recognition画像分類を用いるIoT マルウェアの検知手法についての提案eng深層学習http://id.nii.ac.jp/1001/00192051/Conference Paperhttps://ipsj.ixsq.nii.ac.jp/ej/?action=repository_action_common_download&item_id=192140&item_no=1&attribute_id=1&file_no=1Copyright (c) 2018 by the Information Processing Society of Japan九州大学九州大学Indian Institute of Technology DelhiRoyal Holloway University of London九州大学九州大学蘇, 佳偉Danilo, Vasconcellos VargasSanjiva, PrasadDaniele, SgandurraYaokai, Feng櫻井, 幸一The Internet has extended by including a large number of IoT devices implemented recently. These devices are smarter due to the stronger computational capability and the interconnection through Internet therefore can deal with much more complicated tasks. On the otherside, there are also more chances for attackers to threaten these things.In this paper, we propose a novel light-weight approach for detecting DDos malware in IoT environments, through malware image and a light-weight convolutional neural network image classifier. The results show that the proposed system can achieve $94.0%$ accuracy for the classification of goodware and DDoS malware.The Internet has extended by including a large number of IoT devices implemented recently. These devices are smarter due to the stronger computational capability and the interconnection through Internet therefore can deal with much more complicated tasks. On the otherside, there are also more chances for attackers to threaten these things.In this paper, we propose a novel light-weight approach for detecting DDos malware in IoT environments, through malware image and a light-weight convolutional neural network image classifier. The results show that the proposed system can achieve $94.0%$ accuracy for the classification of goodware and DDoS malware.ISSN 1882-0840コンピュータセキュリティシンポジウム2018論文集201823233262018-11-09