A novel intrusion detection system for internet of things devices and data

Abstract As we enter the new age of Internet Things (IoT) and wearable gadgets, sensors, embedded devices are extensively used for data aggregation its transmission. The extent processed by IoT networks makes it vulnerable to outside attacks. Therefore, is important design an intrusion detection system (IDS) that ensures security, integrity, confidentiality their data. State-of-the-art IDSs have poor capabilities incur high communication device overhead, which not ideal applications requiring secured real-time processing. This research presents a teaching-learning-based optimization enabled (TLBO-IDS) effectively protects from attacks also low overhead at same time. proposed TLBO-IDS can detect analysis attacks, fuzzing shellcode worms, denial service (Dos) exploits, backdoor tested performance compared with state-of-the-art algorithms. In particular, outperforms bat algorithm genetic (GA) 22.2% 40% respectively.