Use case two: traffic-based intelligent network intrusion detection in IoT

Generally, host intrusion (including device level intrusion) exploits outside world communications, and most of the time a successful host intrusion comes with the success of a network intrusion. For example, in botnets, remote command-and-control servers communicate with the compromised machines to give instructions on operations to execute. More importantly, a large number of insecure IoT devices has resulted in a surge of IoT botnet attacks in worldwide IT infrastructure. The Dyn domain name system (DNS) attack in October 2016 is an example of this, wherein the Mirai botnet commanded 100,000 IoT devices to launch the DDoS attack. This incident impacted many popular websites, including GitHub, Amazon, Netflix, Twitter, CNN, and PayPal. In this context, detection of network-level intrusion in IoT is not...