Introduction
The rapid evolution of smart home technologies has significantly enhanced home security, focusing on detecting intrusions and anomalies. One novel approach is the use of Physical Guards, designed to monitor and protect the data integrity within a smart home network. This student project is centered on the development and assessment of a physical guard system in a smart home environment in cooperation with M2M solutions. The project involves setting up a sophisticated smart home system, complete with microcontrollers and sensors that mimic real-life scenarios, thus generating relevant data. Students will construct their dataset using this setup and simulate potential security breaches. This project provides valuable experience in implementing smart home security solutions and contributes to the broader understanding of AI's role in predicting and preventing security breaches in our increasingly connected world. Furthermore, it combines modern AI technologies with IT security models.

The system should:

  1. Utilization of Physical Signal Properties: Employing Software-defined Radios (SDRs), the project aims to leverage physical signal properties as features, thereby exploring their potential applications.
  2. Anomaly Detection: The system must efficiently identify irregularities in both univariate and multivariate physical signals' data, drawing from the data generated by the smart home test setup. This entails the recognition of patterns and deviations within a complex array of physical data, ensuring precise detection of any abnormal activity and/or environmental changes.
  3. Environment Profiling: The system should possess the capability to differentiate certain devices and device sets based on recorded physical signals, as well as deviations within the overall environment.
  4. Adversary Modeling: The team members are tasked with developing an attacker model that encompasses targeted security objectives. Additionally, they are to strategize countermeasures to fortify their model against potential adversaries.
     

Programming language and tools:
Python has been designated as the primary programming language owing to its extensive utilization in AI and signal processing endeavors. Additionally, GNURadio, a software tool for signal analysis, will be employed. In GNURadio, various blocks can be readily accessed through a What-You-See-Is-What-You-Get (WYSIWYG) interface, while custom Python blocks can be implemented within the framework. GNURadio can be installed via Anaconda under the moniker RadioConda.

Hardware:
It is anticipated that software-defined radios (SDRs) from Ettus Research, such as the B200 mini and B210, will be employed. These SDRs can be seamlessly integrated into the GNURadio platform. These devices possess the capability to capture transmitted signals along with their full complement of physical properties. Additionally, they are equipped to transmit self-created signals via a GNURadio flowgraph.