An Exploratory Data Analysis of the Network Behavior of Hive Home Devices

Abstract

Smart homes are gaining more popularity by the day due to the ease they provide in terms of running our homes. However, the energy and resource constrained nature of the smart home devices make security integration challenging, thus making them prone to cyber-attacks. This calls for a need to carry out extensive research on the behavior of these devices in order to design and incorporate better security tailored to their behavior. This paper collects traffic from the Hive home network and carries out an Exploratory Data Analysis (EDA) in terms of their behavior due to the lack of attention they face from the research community despite being one of the largest smart home service providers in the UK. The areas covered are device identification, traffic classification, device mode of control identification, flow volume, flow duration and protocols utilized by these devices both in active and idle states. Some of the covered areas involve components, which are exploited and used maliciously in DDoS flooding attacks, thus this paper compares the normal behavior of these components, to when they are exploited during attacks and in turn giving the end user what to watch out for in the case of an attack.

Detection of DDoS Attack on Smart Home Infrastructure Using Artificial Intelligence Models

“…1. Smart Home Architecture [25] Fig2. DoS attack on smart home architecture [24] To explore data in depth, the Exploratory Data Analysis (EDA) is performed before processing ML algorithms on the data.…”