The past years have witnessed an increasing interest and concern regarding the development of security monitoring and management mechanisms for Critical Infrastructures, due to their vital role in ensuring the availability of many essential services. This task is not easy due to the specific characteristics of such systems, and the natural resistance of Critical Infrastructures operators against actions implying downtime. Digital Twins, as accurate virtual models of physical objects or processes, can provide a faithful environment for security analysis or evaluation of potential mitigation strategies to be deployed in face of specific situations. Nonetheless, their on-premises deployment can be expensive, implying a significant CAPEX whose return will depend on the ability to plan and deploy a suitable support infrastructure, as well as implementing efficient and scalable data collection and processing mechanisms capable of taking advantage of the acquired resources. This paper presents an off-premises approach to design and deploy Digital Twins to secure critical infrastructures, developed in the scope of the ELEGANT project. Such Digital Twins are built using real-time, high fidelity replicas of Programming Logic Controllers, coupled with scalable and efficient data collection processes, supporting the development and validation of Machine Learning models to mitigate security threats like Denial of Service attacks. The validation approach of ELEGANT, which leveraged from the capabilities of the Fed4Fire federated testbeds evaluated the feasibility of using cloudified Digital Twins, thus converting a significant part of the projected CAPEX for the in-premises model into on-demand, pay-as-you-go OPEX, eventually paving the way for the establishment of a DTaaS (Digital Twin as a Service) paradigm. The achieved results demonstrate that the data pipelines providing support for the ELEGANT Digital Twins have low impact in terms of resource usage in Denial of Service and Distributed Denial of Service attack scenarios, when higher volumes of data are generated.

The goal of this work is to investigate the possibility of improving current gamma/hadron discrimination based on the shower patterns recorded on the ground. To this end, we propose the use of Convolutional Neural Networks (CNNs) for their ability to distinguish patterns based on automatically designed features. In order to promote the creation of CNNs that accurately uncover the hidden patterns in the data, and at the same time avoid the burden of hand-crafting the topology and learning hyper-parameters we resort to NeuroEvolution; in particular, we use Fast-DENSER++, a variant of Deep Evolutionary Network Structured Representation. The results show that the best CNN generated by Fast-DENSER++ improves by a factor of 2.37 when compared to the results reported by classical statistical approaches. Additionally, we experiment ensembling the best-generated CNNs; the ensemble leads to an improvement by a factor of 2.48. These results establish a new state-of-the-art in the gamma/hadron discrimination problem, based on the ground impact patterns, and thus prove that CNNs automatically discovered by Fast-DENSER++ can be used to enable investment savings due to the need for smaller grids of sensors.

Computational creativity seeks to understand computational mechanisms that can be characterized as creative. The creation of new concepts is a central challenge for any creative system. In this article, we outline different approaches to computational concept creation and then review conceptual representations relevant to concept creation, and therefore to computational creativity. The conceptual representations are organized in accordance with two important perspectives on the distinctions between them. One distinction is between symbolic, spatial and connectionist representations. The other is between descriptive and procedural representations. Additionally, conceptual representations used in particular creative domains, such as language, music, image and emotion, are reviewed separately. For every representation reviewed, we cover the inference it affords, the computational means of building it, and its application in concept creation.