Smart Security Lab

Intro

SmartSecLab's research and developement is focused on new Artificial Intelligence-based cybersecurity methods towards safer, sustainable, and energy-efficient Smart Environments. The omnipresence of smart appliances and Internet of Things devices undoubtedly brought convenience and a great extent of automation in everyday life. Our goal is to develop novel data-driven methods to be used on tiniest components of Smart Environment infrastructure to guard privacy and ensure security. Artificial Intelligence AI has proven to be an efficient and resilient measure to combat cybercrimes when it comes to Big Data. The research activities are aimed at different areas both in software development and IoT hardware-wise design approach. The lab is hosted at the School of Economics, Innovation ad Technology, Kristiania University College and utilizes both national and international experience in a given domain supported by a public-private partnership and industrial collaboration.

Members of the lab are involved in teaching at Kristiania Univeristy College in the following educational programs:

• Bachelor in Cybersecurity
• Master in Cybersecurity
• Experience-based Master in Cybersecurity

Mission

Rapid boosted digitalization through the last decade and worldwide orientation towards smarter and greener environments has resulted in many cities becoming more intelligent when it comes to automation and natural resources utilization. Our lab is hosted in Oslo, Norway and European Green Capital 2019 award by European Omission was given to Oslo city for extraordinary work towards future smart cities. Moreover, the Oslo city government has launched the Oslo Smart City Strategy to support all “green” initiatives and make sure that the city is being developed accordingly across multiple critical sectors. This approach is getting integrated through a variety of projects in other Norwegian cities. On the international level, Singapore and Dubai can be seen as role models that already have a synergy of technology, data analytics and safety regulations. Our lab's vision is to work on developing international expertise and relevant methods that will support also following Sustainable Development Goals as defined by United Nations: Goal 11 – “Make cities inclusive, safe, resilient and sustainable” and Goal 9 - “Build resilient infrastructure, promote sustainable industrialization and foster innovation”. Ongoing work already resulted in international publications, national and international research project proposals, workshops and joint research initiatives.

Core research objectives:

• Building Deep Learning energy-efficient methods for network data processing
• Researching new cybersecurity frameworks for resource-constrained environments
• New security reference models for Smart Environments
• Developing “green” AI-protected IoT devices
• Rethinking cybersecurity in the domain of Smart Applications
• Establishing Security-as-a Service distributed monitoring over IoT ecosystem

Team

Andrii Shalaginov (Head of lab, Associate Professor)

Bithi Banik (PhD student)

Debasish Ghose (Associate Professor)

Gebremariam Assres (Associate Professor)

Guru Prasad Bhandari (Software Engineer)

Huamin Ren (Associate Professor)

Nikola Gavric (PhD student)

Nisarg Mehta (PhD student)

Nurul Momen (Associate Professor)

Toktam Ramezanifarkhani (Associate Professor)

Tor-Morten Grønli (Professor)

Former members

Andreas Lyth (Hardware Engineer)

projects

ENViSEC: Artificial Intelligence-enabled Cybersecurity for Future Smart Environments (NGI Pointer 2021-current funding)

The overall vision of ENViSEC project is to enhance Smart Environments cybersecurity by introducing intelligent multi-agent data handling, cyber threats sharing, situational awareness and data streams aggregation from Edge devices. Our ambition is to offer a resilient response to cyber-attacks as well as to ensure human-oriented warning and early detection of adversarial actions. Our new method enables multi-level data collection and off-chip Machine Learning model training to reduce the overhead and latency of the Internet of Things (IoT) components. It will contribute towards hardening cybersecurity in a cross-sector context and building an efficient infrastructure in a resource-constrained environment.

SecureUAV: Energy-efficient malware detection in Unmanned Aerial Vehicles via advanced AI models (NGIAtlantic 2022 program)

In this project, the goal is to develop a platform and framework for increased cybersecurity protection and end-user awareness of cyberthreats in unmanned aerial vehicles (UAV). Through AI and human-understandable decision support models, we will build and evaluate a resilient mechanism to detect malicious activities and cyber-physical threats as well as to ensure a timely incident response by drone operator. Moreover, the goal is to propose a cybersecurity-awareness protocol and ensure energy-efficient communication. This research is aimed at bridging and strengthening the EU-US cooperation in the area of AI-enabled cybersecurity between Songlab at Embry-Riddle Aeronautical University in Florida and SmartSecLab at Kristiania University College.

DigForAsp - Digital forensics: evidence analysis via intelligent systems and practices (CA17124 is funded by the European Cooperation in Science and Technology (COST) for 2018-2023)

Digital forensics is a part of the Criminalistics Sciences which deals with digital evidence recovery and exploitation in the solution of criminal cases through the application of scientific principles. There are several and increasingly sophisticated methods for collecting digital evidence. As a matter of fact, the evolution of technology continuously pushes such kind of methods. Rough evidence must however be used to elicit hypotheses concerning events, actions and facts (or sequences of them) with the goal to obtain evidence to present in court. Evidence analysis involves examining fragmented incomplete knowledge, and reconstructing and aggregating complex scenarios involving time, uncertainty, causality, and alternative possibilities. No established methodology exists today for digital evidence analysis. The Scientific Investigation experts usually proceed by means of their experience and intuition. The Challenge of the proposed COST Action consists in creating a Network for exploring the potential of the application of Artificial Intelligence and Automated Reasoning in the Digital Forensics field, and creating synergies between these fields. Specifically, the challenge is to address the Evidence Analysis phase, where evidence about possible crimes and crimes perpetrators collected from various electronic devices (by means of specialized software, and according to specific regulations) must be exploited so as to reconstruct possible events, event sequences and scenarios related to a crime. Evidence Analysis results are then made available to law enforcement, investigators, public prosecutors, lawyers and judges: it is therefore crucial that the adopted techniques guarantee reliability and verifiability, and that their result can be explained to the human actors.

Partners

Established international cooperation partners in the area of cybersecurity:

• ABB, Sweden
• AGH University of Science and Technology, Poland
• Auckland Institute of Technology, New Zealand
• Binare, Finland
• Charles Darwin University, Australia
• Embry-Riddle Aeronautical University, USA
• iHomeLab, Switzerland
• iSolutions Labs, Ukraine
• KTH Royal Insitute of Technology, Sweden
• Pukhov Institute for Modelling in Energy Engineering, Ukraine
• Regulatory Agency for Electronic Communications and Postal Service, Serbia
• Singidunum Univeristy, Serbia
• Soongsil University, South Korea
• University of Jyväskylä, Finland
• Tallinn University of Technology, Estonia

Contact

Please, reach out if you are interested in open positions, project cooperation and if you have any other inquiries.

• Twitter
• Facebook
• Instagram
• GitHub

Elements

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';