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 on Machine Learning for the Detection and Identification of Attacks in the Internet of Things

Research Topics on Machine Learning for the Detection and Identification of Attacks in the Internet of Things

PhD Research Topics on Machine Learning for the Detection and Identification of Attacks in the Internet of Things

Internet of Things (IoT) is the most influencing and versatile technology in every part of the world by expanding communication and networking anytime, anywhere. IoT includes a host of network-connected devices ranging from smartphones to smart appliances and industrial equipment. Network security and data privacy are the most important issue in Iot with the massive use of the internet. Attacks in IoT seek to gather access to IoT devices to cause harm to the devices, which then leads to affects the system’s security and privacy. IoT attacks include spoofing attacks, denial of service (DoS) attacks, jamming, and eavesdropping. Most of the existing security solutions for IoT attacks lead to high computation and communication load to the IoT devices. Traditional security solutions are IoT authentication, access control, secure offloading, and malware detection. Traditional security solutions are integrated with machine learning that provides high performance and security from attacks.

Machine learning techniques possess the ability to detect and protect the IoT system when it is in an abnormal state. Techniques for detecting and identifying attacks in IoT using machine learning are categorized as supervised, unsupervised, and reinforcement learning. Support vector machines (SVMs), naive Bayes, K-nearest neighbor (K-NN), neural networks (NNs), deep NNs (DNNs), random forest, Q-learning, Dyna-Q, post-decision state (PDS), and deep Q-network (DQN) and infinite Gaussian mixture model (IGMM) are some of the algorithms utilized for the detection and identification of attacks in the IoT. Recent developments on detecting and identifying attacks in IoT using machine learning are false data detection in smart grid, anomaly detection, intrusion detection, block-chain-based attack detection, and many more.

Future scopes of machine learning for detecting and identifying attacks in the IoTs are unknown device recognition, continual learning on new devices, deployment of device identification models, reliable benchmark datasets, controlled imprinting of verifiable patterns, and IoT devices with real-time updates.