2019/03/13 by Fatima Hussain, Rasheed Hussain, Hussain, Fatima +5 · 4 citations
Computer Science · Mathematics · #Advanced Malware Detection Techniques #Anomaly Detection Techniques and Applications #Artificial intelligence #Computer network #Computer science #Computer security #Cryptography #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Internet of Things #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Network Security and Intrusion Detection #Resource (disambiguation) #cs.CR #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1904.05735
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2019/03/13 · arxiv created 2019/03/14 · arxiv updated 2019/04/12 · openalex created_date 2022/07/29 · openalex updated_date 2026/07/28
The future Internet of Things (IoT) will have a deep economical, commercial\nand social impact on our lives. The participating nodes in IoT networks are\nusually resource-constrained, which makes them luring targets for cyber\nattacks. In this regard, extensive efforts have been made to address the\nsecurity and privacy issues in IoT networks primarily through traditional\ncryptographic approaches. However, the unique characteristics of IoT nodes\nrender the existing solutions insufficient to encompass the entire security\nspectrum of the IoT networks. This is, at least in part, because of the\nresource constraints, heterogeneity, massive real-time data generated by the\nIoT devices, and the extensively dynamic behavior of the networks. Therefore,\nMachine Learning (ML) and Deep Learning (DL) techniques, which are able to\nprovide embedded intelligence in the IoT devices and networks, are leveraged to\ncope with different security problems. In this paper, we systematically review\nthe security requirements, attack vectors, and the current security solutions\nfor the IoT networks. We then shed light on the gaps in these security\nsolutions that call for ML and DL approaches. We also discuss in detail the\nexisting ML and DL solutions for addressing different security problems in IoT\nnetworks. At last, based on the detailed investigation of the existing\nsolutions in the literature, we discuss the future research directions for ML-\nand DL-based IoT security.\n