Connected Home Automated Security Monitor (CHASM): Protecting IoT Through Application of Machine Learning

The Internet of Things (IoT) will dramatically transform the home experience, but it presents significant security risks. We propose a system that helps reduce the cognitive load on a user in keeping their smart home network protected. The system helps prevent IoT devices from becoming invisible or forgotten by the user and provides semi-autonomous capability to address key security concerns in the connected home. In this paper, we describe the problem, explain specifications for the system, present our work in IoT discovery and IoT device classification portions of the system, and show initial results related to our efforts exploring novel application of machine learning to build this capability.

[1]  S. Rigatti.  Random Forest. , 2017, Journal of insurance medicine.

[2]  Luís Nunes,et al.  Automatic discovery and classifications of IoT devices , 2017, 2017 12th Iberian Conference on Information Systems and Technologies (CISTI).

[3]  Salim Hariri,et al.  Anomaly behavior analysis for IoT sensors , 2018, Trans. Emerg. Telecommun. Technol..

[4]  Rajkumar Buyya,et al.  Internet of Things: An Overview , 2017, ArXiv.

[5]  Ying Li,et al.  IoT Eye An Efficient System for Dynamic IoT Devices Auto-discovery on Organization Level , 2017, 2017 IEEE 4th International Conference on Cyber Security and Cloud Computing (CSCloud).

[6]  Arsalan Mosenia,et al.  Addressing Security and Privacy Challenges in Internet of Things , 2018, ArXiv.

[7]  Yan Leung Lai.  Universal IOT devices discovery system using protocol-independent network flows characteristics , 2018 .

[8]  Vijay Sivaraman,et al.  Characterizing and classifying IoT traffic in smart cities and campuses , 2017, 2017 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[9]  Kartik Palani,et al.  Invisible and forgotten: Zero-day blooms in the IoT , 2016, 2016 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops).

[10]  Anna L. Buczak,et al.  Detection of Tunnels in PCAP Data by Random Forests , 2016, CISRC.

[11]  Robert C. Atkinson,et al.  Threat analysis of IoT networks using artificial neural network intrusion detection system , 2016, 2016 International Symposium on Networks, Computers and Communications (ISNCC).

[12]  Franziska Roesner,et al.  End User Security and Privacy Concerns with Smart Homes , 2017, SOUPS.

[13]  Wei Zhang,et al.  HoMonit: Monitoring Smart Home Apps from Encrypted Traffic , 2018, CCS.

[14]  Jorge Sá Silva,et al.  Security for the Internet of Things: A Survey of Existing Protocols and Open Research Issues , 2015, IEEE Communications Surveys & Tutorials.