Performance Analysis Of Network Anomaly Detection Systems in Consumer Networks

EasyChair Preprint 2512

Abstract

There has been a significant increase in the amount of smart home appliances such as intelligent thermostats, internet connected baby monitors, lights being used, these devices have been a target for a number of cyber-attacks till date. Using only fundamental network information such as Source and Destination Ports, Packet Sizes, TCP Flags, Time between subsequent packets, necessary features can be extracted to detect the aforementioned anomalies. This paper aims analyze some critical operating system performance metrics on detecting such anomalies. It also consists of the taxonomy of various approaches to classify anomalies and detailed description on capturing and cleaning network packets.

Keyphrases: IoT, anomaly detection, machine learning, performance analysis

@booklet{EasyChair:2512,
  author    = {Darsh Patel and Rahul Raman},
  title     = {Performance Analysis Of Network Anomaly Detection Systems in Consumer Networks},
  howpublished = {EasyChair Preprint 2512},
  year      = {EasyChair, 2020}}