Two-Dimensional Projection-Based Wireless Intrusion Classification Using Lightweight EfficientNet

作     者：Muhamad Erza Aminanto Ibnu Rifqi Purbomukti Harry Chandra Kwangjo Kim 

作者机构：School of Strategic and Global StudiesUniversitas IndonesiaDepok16424Indonesia National Institute of Information and Communications Technology(NICT)Koganei184-8795Japan Department of Electrical Engineering and Information TechnologyUniversitas Gadjah MadaYogyakarta55281Indonesia School of ComputingKorea Advanced Institute of Science and Technology(KAIST)Daejeon34141Korea 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第72卷第9期

页      面：5301-5314页

核心收录：

学科分类：0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0805[工学-材料科学与工程（可授工学、理学学位）] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Universitas Indonesia  UI 

主　　题：Intrusion detection impersonation attack convolutional neural network anomaly detection 

摘      要：Internet of Things(IoT)networks leverage wireless communication protocols,which adversaries can *** attacks,injection attacks,and flooding are several examples of different attacks existing in Wi-Fi *** Detection System(IDS)became one solution to distinguish those attacks from benign *** learning techniques have been intensively utilized to classify the ***,the main issue of utilizing deep learning models is projecting the data,notably tabular data,into an *** study proposes a novel projection from wireless network attacks data into a grid-based image for feeding one of the Convolutional Neural Network(CNN)models,*** define the particular sequence of placing the attribute values in a grid that would be captured as an *** the most important subset of attributes and EfficientNet,we aim for an accurate and lightweight IDS module deployed in IoT *** examine the proposed model using the Wi-Fi attacks dataset,called the AWID2 *** achieve the best performance by a 99.91%F1 score and 0.11%false-positive *** addition,our proposed model achieved comparable results with other statistical machine learning models,which shows that our proposed model successfully exploited the spatial information of tabular data to maintain detection accuracy.