A comprehensive survey on machine learning approaches for malware detection in IoT-based enterprise information system

被引:105
作者
Gaurav, Akshat [1 ]
Gupta, Brij B. [2 ,3 ,4 ]
Panigrahi, Prabin Kumar [5 ]
机构
[1] Ronin Inst, Montclair, NJ USA
[2] Natl Inst Technol, Dept Comp Engn, Kurukshetra, Haryana, India
[3] Asia Univ, Dept Comp Sci & Informat Engn, Taichung 413, Taiwan
[4] Staffordshire Univ, Stoke On Trent ST4 2DE, Staffs, England
[5] Indian Inst Management Indore, Indore, India
关键词
Network function virtualisation; enterprise information system; IoT; malware detection; adversarial malware detection; malware visualisation techniques; sandboxing; FEATURE-SELECTION; DEEP; NETWORKS; DEFENSE; ATTACKS; DDOS; VIRTUALIZATION; FRAMEWORK; INTERNET; TAXONOMY;
D O I
10.1080/17517575.2021.2023764
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The Internet of Things (IoT) is a relatively new technology that has piqued academics' and business information systems' attention in recent years. The Internet of Things establishes a network that enables smart devices in an organisational information system to connect to one another and exchange data with the central storage. Android apps are placed on Android apps to enhance the user-friendliness of IoT devices in business information systems, making them more interactive and user-friendly. However, the usage of Android apps makes IoT devices susceptible to all forms of malware attacks, including those that attempt to hack into IoT devices and get access to sensitive information stored in the corporate information system. The researchers offered a variety of attack mitigation approaches for detecting harmful malware embedded in an Android application operating on an IoT device. In this context, machine learning offered the most promising strategies to detect malware attacks in IoT-based enterprise information systems because of its better accuracy and precision. Its capacity to adapt to new forms of malware attacks is a result of its learning capabilities. Therefore, we conduct a detailed survey, which discusses emerging machine learning algorithms for detecting malware in business information systems powered by the Internet of Things. This article reviews all available research on malware detection, including static malware detection, dynamic malware detection, promoted malware detection and hybrid malware detection.
引用
收藏
页数:25
相关论文
共 162 条
[31]   Softwarization and virtualization in 5G mobile networks: Benefits, trends and challenges [J].
Condoluci, Massimo ;
Mahmoodi, Toktam .
COMPUTER NETWORKS, 2018, 146 :65-84
[32]  
Cook D.J. Holder., 2006, MINING GRAPH DATA
[33]  
Dai SF, 2013, IEEE INFOCOM SER, P809
[34]   Evading Classifiers by Morphing in the Dark [J].
Dang, Hung ;
Huang, Yue ;
Chang, Ee-Chien .
CCS'17: PROCEEDINGS OF THE 2017 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2017, :119-133
[35]  
Davidsen SA, 2015, 2015 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI), P1366, DOI 10.1109/ICACCI.2015.7275803
[36]   DDoS-Capable IoT Malwares: Comparative Analysis and Mirai Investigation [J].
De Donno, Michele ;
Dragoni, Nicola ;
Giaretta, Alberto ;
Spognardi, Angelo .
SECURITY AND COMMUNICATION NETWORKS, 2018,
[37]   Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection [J].
Demontis, Ambra ;
Melis, Marco ;
Biggio, Battista ;
Maiorca, Davide ;
Arp, Daniel ;
Rieck, Konrad ;
Corona, Igino ;
Giacinto, Giorgio ;
Roli, Fabio .
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING, 2019, 16 (04) :711-724
[38]  
Department of Computer Science Federal University Wukari Wukari Nigeria., 2018, International Journal of Advanced Research in Computer Science, V9, P504, DOI [10.26483/ijarcs.v9i1.5429, 10.26483/ijarcs.v9i1.5429, DOI 10.26483/IJARCS.V9I1.5429]
[39]  
Department of Computer Science Virtual University of Pakistan, 2018, International Journal of Education and Management Engineering, V8, P20, DOI [10.5815/ijeme.2018.02.03, DOI 10.5815/IJEME.2018.02.03]
[40]  
Desnos A., 2011, ANDROGUARD