Abstract

Smart-home installations exponential growth has raised major security concerns. To this direction, the GHOST project, a European Union Horizon 2020 Research and Innovation funded project, aims to develop a reference architecture for securing smart-homes IoT ecosystem. It is required to have automated and user friendly security mechanisms embedded into smart-home environments, to protect the users’ digital well being. GHOST project aims to fulfill this requirement and one of its main functionalities is the traffic monitoring for all IoT related network protocols. In this paper, the traffic capturing and monitoring mechanism of the GHOST system, called NDFA, is presented, as the first mechanism that is able to monitor smart-home activity in a holistic way. With the help of the NDFA, we compile the GHOST-IoT-data-set, an IoT network traffic data-set, captured in a real world smart-home installation. This data-set contains traffic from multiple network interfaces with both normal real life activity and simulated abnormal functioning of the devices. The GHOST-IoT-data-set is offered to the research community as a proof of concept to demonstrate the ability of the NDFA module to process the raw network traffic from a real world smart-home installation with multiple network interfaces and IoT devices.

Highlights

  • Without a doubt, the Internet of Things (IoT) has attracted considerable attention during the last years, as the related technology presents a huge investment opportunity for many industrial and business stakeholders

  • The most prominent example is the break out of the Mirai botnet, where the use of default authentication credentials allowed the cyber-crooks to take over hundreds of thousands of IoT devices with the purpose to entangled them in Distributed Denial of Service (DDoS) attacks [3]

  • /ghost-iot-dataset) to demonstrate the ability of the NDFA module to process the network traffic of a smart-home. This way, we offer to the research community a public data-set containing IoT network traffic collected from a real life smart-home installation

Read more

Summary

Introduction

The Internet of Things (IoT) has attracted considerable attention during the last years, as the related technology presents a huge investment opportunity for many industrial and business stakeholders. The GHOST’s module responsible for the risk assessment evaluates the risk against the smart-home environment and either according to the user’s preferences or autonomously it proceeds to the mitigation measures for the identified risk As it is evident, the input of the GHOST solution, namely the raw network traffic, is of the utmost importance for the accurate and timely detection of the cyber-security events. In the context of the GHOST project, we deploy the NDFA module in a real life smart-home installation to collect actual network traffic for the testing and evaluation of the GHOST solution. /ghost-iot-dataset) to demonstrate the ability of the NDFA module to process the network traffic of a smart-home This way, we offer to the research community a public data-set containing IoT network traffic collected from a real life smart-home installation.

Related Work
Data-Sets
Data Inspection Work-Flow
Data Capturing
IP Traffic Work-Flow
IP Packets Analysis
IP Flows Analysis
Non-IP Protocols Work-Flow
Packet Analysis
Batches Analysis
IP Traffic Data Format
Data Flows Analysis
Packet Batches Analysis
Real World Smart-Home Data-Set
Environment
Installation Description
Capturing
Data-Set Analytics
10 October 2019
Conclusions

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.