Taxonomy and challenges in machine learning-based approaches to detect attacks in the internet of things

摘要: The insecure growth of Internet-of-Things (IoT) can threaten its promising benefits to our daily life activities. Weak designs, low computational capabilities, and faulty protocol implementations are just a few examples that explain why IoT devices nowadays highly prone cyber-attacks. In this survey paper, we review approaches addressing problem. We focus on machine learning-based solutions as representative trend in the related literature. classify Machine Learning (ML)-based techniques suitable for construction Intrusion Detection Systems (IDS) IoT. contribute with detailed classification each approach based own taxonomy. Open issues research challenges also discussed provided.