Securing the Internet of Things and Wireless Sensor Networks via Machine Learning: A Survey

Machine Learning Threatens 5G Security

“…There are many different usecases for ML in each of these categories spanning from enduser devices and access networks to operators' central clouds. For example, ML will be applied in the access network to increase spectral efficiency or for other intelligent use of radio resources [27]; in the edge near the access network to intelligently serve latency-critical services by providing higher resources in the edge [28] and IoT [29]; in the backhaul or transport network for traffic classification [30] or improving network management with the help of SDN [31]; and for improving the performance of cloud-based services [32], [33].…”

Otimização do Consumo de Energia em Redes Ad Hoc Aloha Empregando Deep Learning

“…Para resolução desses problemas, trabalhos como [Mohammadi et al 2018, Mamdouh et al 2018] aplicam técnicas de classificação e regressão com Aprendizagem Profunda (Deep Learning) em diversasáreas de redes de comunicação, demonstrando um desempenho promissor em várias tarefas como identificação de fluxo, detecção de intrusão, roteamento, compressed sensing, predição de tráfego e detecção de sinais, por exemplo. [Mao et al 2018] propõe o uso de Deep Learning para aproximação de algoritmos exatos, agregando baixo volume de processamento de dadosà resoluções matemáticas eficientes.…”

Machine Learning Meets Communication Networks: Current Trends and Future Challenges

“…Leading to the recent development in ML, an introduction of ML with applications to communication systems is provided in [41]. The article introduces the key concepts of ML, mainly focusing on supervised and unsupervised learning, and discusses using ML for the physical layer at the edge and [26] Techniques for Internet traffic classification using ML Main focus on traffic classification techniques 2010 [27] Bio-inspired networking and nano-communications The main focus is on nano-networks, sensors and actuators 2010 [28] State-of-the-art of ML-based intrusion detection systems Focuses only on improving security using ML 2014 [29] Bio-inspired and swarm intelligence-based networking Limited discussion on novel technologies, e.g., SDN, NFV 2014 [30] A survey on using ML for WSNs The article is focused on sensor networks only 2015 [31] Opportunities and challenges in ML for HetNets Short article and limited in scope 2016 [32] A survey on data mining techniques for IDSs Focuses only IDSs using data mining 2017 [33] A survey on DL for intelligent network traffic control Mainly focused on the network layer 2017 [34] A survey on ML and Big Data mechanisms for IoT Broadly covering the scope of IoT and its requirements 2018 [35] A survey on using ML for securing IoT and WSNs Focuses only on security of IoT and WSNs using ML 2018 [36] A survey on security of ML techniques Limited in scope to discussion on security of ML 2018 [37] A survey on DL for Intelligent Wireless Networks Lacks recent trends in MEC, SDN, and NFV, etc. 2018 [38] A survey of ML techniques for optical networks Limited in scope to optical networks 2018 [39] An overview of ML techniques for optical networks Limited in scope for wireless networking technologies 2018 [40] Big data analytics and ML in future wireless networks Not comprehensive on networking technologies 2018 [41] Overview of ML applications in communication systems Mainly focused on edge, cloud and physical layer 2019 [9] An extensive survey on DL for wireless networks Lacks discussion on emerging technologies, e.g., SDN, MEC 2019 [42] A state-of-the-art study on ML in SDN Focuses only on SDN 2019 [43] Application and challenges of RL and DRL in 5G Focuses only RL and DRL and does not cover all the layers 2019 [44] Application of DRL in communication networks Limited in scope on MEC, SDN, NFV, etc.…”

“…The article describes the advantages and disadvantages of various algorithms in particular scenarios and presents a guide for WSN designers to select the right ML algorithms. A brief survey on using ML for securing IoT and WSNs is presented in [35]. Various types of attacks on WSNs are presented followed by the overview of different solutions that use ML to secure the networks.…”

“…Content may change prior to final publication. [26] Internet traffic classification [28] ML techniques for improving security [27] Bio-inspired networking [30] Techniques of ML for sensor networks [29] Swarm intelligence-based networking [31] ML for HetNets, opportunities & challenges [32] Data mining techniques for IDS [34] ML and BD techniques for IoT [33] Intelligent traffic control using ML [39] ML for optical networks [40] BDA and ML for wireless networks [37] DL for intelligence in wireless networks [36] Security of ML techniques and algorithms [35] ML for IoT (sensor networks) security [9] DL for wireless networks [42] ML mechanisms for SDN [44] DRL in communication networks [43] DRL in 5G and beyond [46] ML in SDN concepts [50] ML in 5G and beyond [54] Proactive optimization in 5G using ML [53] Latency improvement through ML [51] ML history in wireless networks [52] ML in edge and cloud [55] A survey of federated learning in MEC [25] White paper on the role of ML in 6G Our article ML for communication networks networks. Related to 5G, the article discusses the potential use of ML in enhanced mobile broadband, massive machinetype communications, and ultra-reliable low latency communications.…”