CISSAN (Collective intelligence supported by security aware nodes)
CISSAN builds methods and technology for integrating collective security intelligence to IoT networks. CISSAN-powered networks will be able to collaboratively identify tampered and adversarial devices, detect malicious activities, and select effective countermeasures. Higher IoT network resilience with be accompanied by resource efficiency through intelligent distribution of security functionalities across network nodes. CISSAN is EU CELTIC-NEXT project (https://www.celticnext.eu/project-cissan/). In Finland CISSAN belongs to Bittium´s Seamless and Secure Connectivity program funded by Business Finland.
Main focus
The proliferation of Internet of Things (IoT) has fundamentally changed how different environments, such as homes, offices, factories, smart buildings, and smart grids, are used and operated. However, security is a major concern for IoT networks and environments, where the risks of physical device tempering, injection of malicious devices, and unpatched vulnerabilities are higher than in traditional networks. CISSAN proposes and implements algorithms for mitigating IoT security threats through collective decision-making and with a reduced impact on the limited resources of IoT devices. These algorithms will be based on research and innovation in optimizing the distribution of security capabilities and aggregating the intelligence in IoT network nodes. Three industrial use cases, which nowadays heavily rely on the use of IoT, will inform the project developments and will be used for validating and demonstrating the project results: (i) public transportation; (ii) smart energy grids; (iii) mining and tunneling operations.
Approach
CISSAN will research and implement algorithms for distributed security monitoring, attack detection and response in IoT networks. Such algorithms will combine machine learning-based methods, more traditional AI techniques (e.g., decision-making based on formal knowledge representation and expert systems, fuzzy logic-based approaches, or genetic algorithms), and attack-specific rules. Since increasing the level of autonomy in IoT network defence is one of the high goals of the project, we will propose mechanisms for collective decision-making by CISSAN “security agents”, which are essentially security functions placed to IoT network nodes. Blockchain-based consensus protocols are one possible type of such mechanisms to be considered in the project. To enable communication between the security agents, CISSAN will implement a light overlay networking solution. Also, methods and tools will be developed for verifying the quality of data sets used in the project for building machine learning models and supporting other data-driven technologies.
IoT devices are usually resource-constrained, and instrumenting each of them with the full set of security functions required for detecting and countering cyberattacks may not be an optimal strategy. Instead, we will propose network context-aware algorithms for distributing the security functions among the IoT devices, edge devices, and possibly cloud backends to achieve a suitable balance between the network resilience and the resource utilization.
The technical efforts in CISSAN will be accompanied by defining and investigating potential business models around the project results and their business impact analysis. Regulatory and compliance considerations will be taken into account, including the ENISA’s work on certification schemes.
Partners
AddSecure Smart Grids (SE), Affärsverken Karlskrona (SE), Arctoslabs AB (SE), Blekinge Tekniska Högskolan (SE), Blue Science Park (SE), Cibernos (ES), Clavister AB (SE), Councilbox (ES), Geodata Ziviltechnikergesellschaft mbH (AT), Mattersoft Ltd. (FI), Mint Security Ltd. (FI), Netox (FI), Nodeon Finland Oy (FI), Savantic (SE), ScopeSensor Ltd. (FI), Techinova AB (SE), University of Jyväskylä (FI), Wirepas Oy (FI)
Contact
Contact for the CISSAN project is [email protected]
