Operational Technology (OT) systems are essential for industrial processes but increasingly face cyber threats due to their integration with IT networks. This paper introduces an advanced framework for modeling, analyzing, and mitigating OT cyber risks using logical attack graphs with OT-specific modeling, including protocols, device hierarchies, and multi-layer dependencies. To enhance scalability, a novel graph pruning algorithm eliminates 81% to 98% of redundant nodes, reducing complexity while preserving critical attack paths. Additionally, an automated validation pipeline bridges theoretical modeling and real-world applicability by refining attack graphs and providing actionable mitigation insights. The framework’s modular and adaptable design ensures it remains effective in evolving OT environments, addressing emerging threats with high resilience. Validation in realistic OT scenarios confirms its scalability and effectiveness, making it a practical, extensible cybersecurity solution for protecting industrial infrastructures and critical processes from advanced cyber risks.

ASTERIA is the new AlphaWaves project developed within the framework of the CIM4.0 initiative, dedicated to the analysis and simulation of intelligent industrial infrastructures. The initiative aims to create an advanced virtual environment for testing network architectures and emerging technologies in the context of Industry 4.0, combining modeling approaches, digital twins, and machine learning. The project enhances AlphaWaves’ expertise in integrating heterogeneous data and developing plug-and-play simulation solutions, designed to accelerate the deployment of secure, resilient, and high-performance industrial systems. ASTERIA is envisioned as a digital laboratory for innovation in production processes, supporting both SMEs and large enterprises in their transition toward the factory of the future.

Hypoxia occurs when blood or tissues are deprived of adequate oxygen, posing a significant risk to military aircrew operating at high altitudes due to reduced atmospheric pressure. The danger lies in its subtle symptoms—such as impaired judgment—often unnoticed until serious consequences arise. While hypoxia can be detected using direct (e.g., pulse oximetry), indirect (e.g., PPG), or tissue-level (e.g., NIRS) methods, these are often impractical in flight settings due to motion artifacts, low perfusion, or invasiveness. This study aims to develop and internally validate machine learning models to classify hypoxic conditions in military aircrew members using electrocardiogram (ECG) and skin temperature signals, offering a non-invasive and real-time monitoring approach. Methods: Data were collected from healthy military aircrew members undergoing standardized hypoxia training in a hypobaric chamber simulating high-altitude conditions. ECG, skin temperature, and respiration signals were recorded using wearable sensors. Hypoxia events were labeled based on oxygen mask removal at altitude. A multi-window feature extraction approach was applied using time windows of 20–120 seconds, enabling trend detection across scales. In total, 87 ECG-derived features were combined with temperature and respiration features. After preprocessing and quality control, a feature selection strategy based on repeated classifier rankings was employed. Five classifiers were trained and evaluated (Support Vector Classification, Decision Tree, Random Forest, Logistic Regression, K-Nearest Neighbors) using cross validation and accuracy and log loss metrics. Results: Data from 40 participants were included after preprocessing. Across classifiers, classification accuracy ranged from 0.85 to 0.90, with the SVC achieving the highest average accuracy (0.90 ± 0.07) and lowest log loss (0.25 ± 0.15). The most informative Online First features came from longer time windows, particularly the 80th percentile of respiratory rate intervals (HRV_Prc80NN), mean respiration rate, and mean skin temperature. Classifier performance was robust across models, with small differences, suggesting that model architecture is less critical than feature representation. Conclusions: We demonstrate that ECG and skin temperature signals can reliably detect hypoxic conditions in military aircrew using machine learning. The approach shows strong internal performance and highlights specific physiological features as key indicators. These findings support the feasibility of real-time, non-invasive hypoxia monitoring in flight environments and lay the groundwork for future applications in other high-risk domains such as commercial aviation, spaceflight, and clinical monitoring. Further research will involve evaluating model performance in operational flight conditions and exploring generalization across individuals and sensor systems.

COMPLAI is the platform developed by AlphaWaves to revolutionize regulatory compliance assessment in Operational Technology (OT) systems. The project integrates Artificial Intelligence (AI) and Explainable AI (XAI) technologies to analyze security and automate the verification of compliance with regulations such as NIS2, DORA, and the Cyber Resilience Act.

Through advanced threat modeling tools and a custom-designed Compliance Scoring engine, COMPLAI enables continuous monitoring of industrial infrastructures, identifying vulnerabilities, misconfigurations, and high-risk behaviors. The platform stands out for its intuitive interface, scalable architecture, and plug-and-play approach, making it seamlessly integrable into real-world production processes without disrupting operations.

The project is carried out in collaboration with industrial partners and is validated on a real-world use case based on a physical OT station combined with a virtual infrastructure.

COMPLAI aims to make OT cybersecurity accessible, objective, and proactive, helping companies strengthen their resilience and transform compliance into a competitive advantage.

COMPLAI is part of the Next Generation EU - PNRR Extended Partnership SERICS, specifically within Spoke 3 “Attacks and Defences,” with a budget of €188,606.00. This initiative underscores the commitment to enhancing cybersecurity in critical infrastructures across Europe, ensuring that OT systems are not only secure but also compliant with evolving regulatory standards.

Misconfigurations within Operational Technology (OT) environments represent a significant source of cyber risk, often resulting in critical disruptions to industrial processes. However, the absence of standardized methodologies for quantifying their impact hinders effective risk assessment and prioritization. This study proposes a novel and fully automated framework that maps misconfigurations to the Common Weakness Enumeration (CWE) taxonomy through semantic similarity techniques, employing state-of-the-art sentence embedding models and cosine similarity metrics. The framework enables the computation of quantitative risk indicators by linking the identified CWEs to associated Common Vulnerabilities and Exposures (CVEs) and aggregating their Common Vulnerability Scoring System (CVSS) scores. A voting ensemble of pre-trained language models is introduced to enhance robustness and semantic accuracy. Experimental validation demonstrates improved precision over single-model baselines, confirming the efficacy of the proposed approach. The resulting system offers a scalable, data-driven tool for OT stakeholders to evaluate and prioritize misconfigurationrelated cybersecurity threats systematically.

In modern digital ecosystems, managing heterogeneous data sources is a significant challenge, particularly within Renewable Energy Communities (RECs), where multiple energy vectors, such as electricity, heating, and water, must be integrated seamlessly. The GAIA meta-platform addresses the persistent fragmentation of IoT ecosystems by enabling federated access, semantic harmonization, and cross-domain analytics across heterogeneous data silos. Designed to support both expert and non-expert users, GAIA combines modular data processing, a Python SDK, and an AI-driven conversational agent (i.e., GAIA Chat) to facilitate intuitive interaction with multi-source datasets. This paper presents the platform’s architecture and functionalities, emphasizing its role in advancing data-driven services for RECs. Finally, a real-world deployment demonstrates GAIA’s ability to integrate energy and water data, enabling advanced use cases such as cross-domain anomaly detection and indirect consumption estimation. The results validate GAIA as a scalable, domain-agnostic infrastructure capable of supporting intelligent services in complex smart environments.

Operational Technology (OT) networks face growing cybersecurity risks, yet applying best practice guidelines remains difficult—particularly in settings with limited cybersecurity expertise. This paper proposes a modular framework combining a Large Language Model (Llama3 8B Instruct), semantic search (FAISS), and structured prompting to assist in the analysis of OT configurations. The system extracts best practices from authoritative sources, generates standardized JSON templates for data collection, and leverages a chatbot assistant for compliance validation and mitigation guidance. Experimental results show moderate accuracy (60–66.67%), highlighting both the promise and current limitations of LLM-based security tools. The framework offers a foundation for enhancing automation, interpretability, and resilience in OT environments.

Abstract: The growing complexity of Industrial Control Systems (ICS) and Operational Technology (OT) networks presents significant challenges in network discovery, device classification, and causal process inference. Traditional methodologies, which depend on manual configurations and static rule-based approaches, often prove inadequate in dynamic industrial environments due to their limited scalability and adaptability. This paper introduces an AI-driven agentic framework designed to automate these critical processes. The proposed system employs autonomous AI agents for real-time network scanning, device identification through communication pattern analysis, and inference of process dependencies. By integrating active and passive data collection into the agents’ workflow, where they receive insights from these analyses as input, our approach extracts system dynamics without requiring prior domain knowledge of industrial processes. This methodology advances industrial automation by enabling adaptive, self-optimizing operations, thereby reducing manual intervention and enhancing system visibility. Moreover, it represents a significant step toward the realization of Digital Twins, while also facilitating predictive maintenance and cybersecurity monitoring. Ultimately, this framework offers a scalable and intelligent solution to support the digital transformation of industrial ecosystems.

In today’s data-driven world, the interconnection and automation of daily processes have become essential. As the demand for Internet connectivity grows, so does the need for robust cybersecurity measures. Operational Technology (OT), pivotal in controlling critical infrastructures such as power plants and water distribution systems, remains highly vulnerable. Many OT systems still rely on ‘air gaps’ for security, a measure increasingly insufficient as more systems connect to the internet for remote operation and data analysis. This article addresses the critical need for enhanced OT security solutions by introducing a novel tool focused on intelligent systems for the effective detection of cyber-attacks. The tool automates the creation of attack graphs and extracts attack paths from a JSON file describing the OT network. Leveraging the MulVAL attack graph generation engine, it provides a comprehensive visualization of potential attack vectors, enhancing the capability to identify and mitigate security threats in OT environments.

Despite of the global environmental crisis with record-high CO2 levels, urgent climate action is imperative. The EU’s ambitious emission reduction targets and the goal of climate neutrality by 2050 underline the severity of the situation. The Italy case study encounters challenges aligning with these objectives, necessitating significant emission cuts despite advancements in renewable energy and reduced energy consumption. Renewable Energy Communities (RECs) emerge as vital players, focusing on local production, consumption, and management of electrical energy. Our research introduces the GAIA federated software metaplatform, addressing the lack of multi-energy vector management by integrating diverse Internet-of-Things (IoT) software infrastructures. It simplifies the development of multi-energy vector services by amalgamating data from federated simple vector IoT infrastructures. GAIA aims to bridge the information gap on resource consumption and interconnections, benefiting RECs citizens and service providers. The platform enhances transparency, facilitating informed decision-making for REC stakeholders and it provides new opportunities and perspectives.

LORAWINE – Il Vino Si Fa in Vigna

A IoT platform for precisely tracing the entire production and transformation chain in vine sector.

With the growth of tourism industry, airplanes have became an affordable choice for medium- and long-distance travels. Accurate forecasting of flights tickets helps the aviation industry to match demand, supply flexibly and optimize aviation resources. Airline companies use dynamic pricing strategies to determine the price of airline tickets to maximize profits. Passengers want to purchase tickets at the lowest selling price for the flight of their choice. However, airline tickets are a special commodity that is time-sensitive and scarce, and the price of airline tickets is affected by various factors.Our research work provides a systematic comparison of various traditional machine learning methods (i.e., Ridge Regression, Lasso Regression, K-Nearest Neighbor, Decision Tree, XGBoost, Random Forest) and deep learning methods (e.g., Fully Connected Networks, Convolutional Neural Networks, Transformer) to address the problem of airfare prediction, by keeping the consumers’ needs. Moreover, we proposed innovative Bayesian neural networks, which represent the first exploitation attempt of Bayesian Inference for the airfare prediction task, to the best of our knowledge. Therefore, we evaluate the performance of our implemented and optimized models on an open dataset. The experimental results show that deep learning-based methods achieve better results on average than traditional ones, while Bayesian neural networks can achieve better performance among the other machine learning methods. However, taking into account both prediction performance and computational time, the Random Forest turns out to be the best choice to apply in this scenario.

GAIA – Gestione Avanzata dell’Idrico e dell’energia nelle comunità Alpine

A platform for a unified and harmonized access to multi-vector data, enabling AI/ML algorithm development.

The GAIA project aim at standardizing the IoT world, by providing a powerful tool to describe data sources and access them in a unified way, as they are one. The focus is on a meta-language to describe data, access it and use it in advanced data analysis methodologies.

Cybersecurity solution for distributed smart warehouses