This ERC project pushes the boundary of reliable data-driven decision making in cyber-physical systems (CPS), by bridging reinforcement learning (RL), nonparametric estimation and robust optimization. RL is a powerful abstraction of decision making under uncertainty and has witnessed dramatic recent breakthroughs. Most of these successes have been in games such as Go - well specified, closed environments that - given enough computing power - can be extensively simulated and explored.
A recent wave of cyberattacks has made it evident that cybercrime is a growing global concern. Numerous threats such as malware infections, phishing attempts and identity thefts can have disastrous consequences for citizens, firms and nations. Cybercrime, defined as crimes where expertise about cyberspace is used to violate the law, is an increasing threat due to criminals’ creativity, faster digitization, growing dependence on technologies and huge data accumulation.
Incoming files present one of the most serious threats to every corporate network. Cyber attackers have the knowledge and resources to implement highly sophisticated attacks using various methods such as encrypted and distributed malware attacks, zero-day attacks and more. These are delivered via files which are introduced into the target network by various channels, including email, removable media, and web download. Malware attacks can create serious damage to the organization but current available defensive measures fail to provide any protection against such attack.
As digitisation becomes a business priority for many organisations in Europe and around the world, the industrial Internet of Things (IIoT) will generate huge opportunities for key industries like manufacturing, oil and gas, agriculture, mining and transportation. IIoT is bringing machines, analytics, and people to form a network of industrial devices connected by communications technologies. Machine-to-machine communication, however, increases the risk of cyberattacks.
AERAS aims to develop a realistic and rapidly adjustable cyber range platform for systems and organisations in the critical healthcare sector, to effectively prepare stakeholders with different types of responsibility and levels of expertise in defending high-risk, critical cyber-systems and organizations against advanced, known and new cyber-attacks, and reduce their security risks.
The EU-funded 5GZORRO project (Zero-touch security and trust for ubiquitous computing and connectivity in 5G networks) will develop these envisaged solutions for zero-touch service, network and security management in multi-stakeholder environments (ubiquitous), making use of Smart contracts based on Distributed Ledgers Technologies to implement required business agility.
The project ELIoT Pro (Easy& Lightweight IoT Protector) an end-to-end cybersecurity solution for IoT networks. For H2M authentication in IoT environments the solution eliminates passwords – nothing for hackers to steal. Our core technology is based on the One-Time Password (OTP) user authentication protocol, mathematically proven unbreakable. For M2M in IoT environments ELIoT Pro ensures secure device-to-device authentication and data security using a lightweight encryption protocol.
The main goal of AF-Cyber is to investigate and analyse the problem of attributing cyber attacks. We plan to construct a logic-based framework for performing attribution of cyber attacks, based on cyber forensics evidence, social science approaches and an intelligent methodology for dynamic evidence collection. AF-Cyber will relieve part of the cyberattacks problem, by supporting forensics investigation and attribution with logical-based frameworks representation, reasoning and supporting tools.
E-CORRIDOR aims at providing a flexible, secure and privacy-aware framework allowing confidential, distributed and edge enabled security services, as threat analysis and prevention as well as privacy-aware seamless access mechanism in multi-modal transport systems.