Internet of Things Garage

Context Aware Security for Smart Homes

Context Aware Security for Smart Homes using Cyber Physical Data Analysis

The rapid growth of the Internet of Things (IoT) requires a deep look into security and privacy challenges. This growth is changing our contemporary world, which is now connected in novel ways and poses new challenges. Nowadays, these tiny little devices (IoTs) routinely communicate with each other on behalf of humans. As we move further into this AI era, the world needs assurance that this fabric of interconnected things is not vulnerable to traditional or cyber-physical security threats. The entire spectrum of IoT fabric includes; devices/things, connectivity, storage, and applications – all of which are potentially vulnerable. In addition to traditional connectivity channels, IoTs are exposed to physical channels such as temperature, humidity, air quality, illumination, sound, and many more. A single vulnerable IoT can be a gateway to break into a secure smart home system by being exploited by a cyber vulnerability or by a physical channel(s).

Assume a temperature sensor in a smart home network is vulnerable and exploited by an adversary. Even if a temperature sensor transmits a high value, it can trigger an open window. Currently, available solutions are mostly focused on traditional Network Traffic Analysis (NTA) for detecting anomalies in cyber systems (Intrusion Detection or Intrusion Prevention), which is not sufficient in the IoT scenario. This project is focused on cyber-physical behaviour, where we aim to detect cyber attacks by detecting anomalies by cyber-physical behavioural data analysis in smart homes. We aim to develop low-cost multi-purpose sensor nodes which can detect anomalies in a smart home by analysing cyber-physical data. In another scenario, imagine a malicious party switch on a toaster at midnight while spoofing the smart plug and preventing it from reporting to the smart home hub. The multi-purpose sensor network we propose can be used to detect such anomaly events by physically observing temperature vibration, light, or sound even though the malicious party may have compromised the smart plug as well the smart home hub preventing it from generating NTA-based anomaly. The project has the following objectives:


Team


Funding

Cardiff University

Cardiff University is the only Welsh member of the Russell Group of research-intensive British universities.


Partners

PETRAS 2

PETRAS National Centre of Excellence for IoT Systems Cybersecurity is a consortium of eleven leading UK universities which will work together over the next three years to explore critical issues in privacy, ethics, trust, reliability, acceptability, and security.

Building Research Establishment (BRE)

The Building Research Establishment (BRE) is a centre of building science in the United Kingdom, owned by a charitable organisation, the BRE Trust. BRE provides research, advice, training, testing, certification and standards for public and private sector organisations in the UK and abroad.

Government Communications Headquarters (GCHQ)

Government Communications Headquarters, commonly known as GCHQ, is an intelligence and security organisation responsible for providing signals intelligence and information assurance to the government and armed forces of the United Kingdom.


Outcomes

Journal
Yasar Majib, Mahmoud Barhamgi, Behzad Momahed Heravi, Sharadha Kariyawasam, Charith Perera Detecting Anomalies within Smart Buildings using Do-It-Yourself Internet of Things, Journal of Ambient Intelligence and Humanized Computing (JAIHC), September 2022
Journal
Yasar Majib, Mohammed Alosaimi, Andre Asaturyan, and Charith Perera Dataset for Cyber-Physical Anomaly Detection in Smart Homes, Frontiers in the Internet of Things, Volume 2, 2023, pp, 1–15