A method for vulnerability detection by IoT network traffic analytics

The Internet of Things comprises wireless devices with limited computing resources. It targets attacks that exploit vulnerabilities such as unencrypted data transfer. Conventional vulnerability detection occurs from databases that list the most common vulnerabilities and exploits (CVEs). However, these bases are limited to known vulnerabilities, which is not the case for the IoT context most of the time. This work proposes MANDRAKE: a Method for vulnerAbilities detectioN baseD on the IoT netwoRk pAcKEt traffic using machine learning techniques. A performance evaluation has been conducted in a smart home scenario taking as basis two datasets, one generated experimentally for this work and the other from the literature. The results have achieved 99% precision in detecting vulnerabilities in network traffic.