Amazing technological breakthrough possible @S-Logix pro@slogix.in

Office Address

  • #5, First Floor, 4th Street Dr. Subbarayan Nagar Kodambakkam, Chennai-600 024 Landmark : Samiyar Madam
  • pro@slogix.in
  • +91- 81240 01111

Social List

Research Topics in Deep Learning-based Attack Detection for RPL Routing Protocol

Research Topics in Deep Learning-based Attack Detection for RPL Routing Protocol

   A network of interconnected smart devices, machines, and related software devices is termed the Internet of Things (IoT). In modern society, IoT plays a crucial role and enables energy-efficient automation to improve the quality of life. A wide range of applications of IoT is in the field of industrial scenarios, smart homes, intelligent healthcare, and smart cities. The importance of IoT applications is to secure the IoT networks from attacks. Cyber-attacks or network attacks in IoT significantly cause disruption and loss of information. Low Power Lossy Network Routing Protocol (RPL) is mainly affected by the attacks on IoT. RPL is an effective protocol that allows communication in a wireless network with low power consumption and limited resources. RPL is effectively used in different applications, including but not limited to healthcare, smart environments, transport, industry, and military application.
    RPL attacks are hard to defend against due to the improvised nature of IoT systems and resource constraints of IoT devices. RPL attacks affect the IoT networks from both the outside and inside the node. Continuous security and robustness against the RPL attacks are needed to achieve the systems confidentiality, integrity, and availability of IoT networks. Some of the RPL attacks are sinkhole attacks, wormhole attacks, persistent attacks, distributed denial-of-service, clone ID, sybil attack, and many more. Deep-learning based method is a successful approach for detecting attacks in RPL and predicting the abnormal and normal behavior of IoT networks. The advantage of deep learning methods over classic machine learning methods is better performance with large, complex, and repetitive datasets.
    Deep learning models handle complex prediction, classification, and detection tasks with high accuracy than machine learning models. Architectures of deep neural networks utilized for deep learning-based attack detection in RPL are multi-layer perceptron (MLP), generative adversarial networks(GAN), deep belief network(DBN), and convolutional neural network(CNN).