https://hdl.handle.net/20.500.11984/14090 Tue, 14 Jul 2026 18:50:13 GMT 2026-07-14T18:50:13Z https://hdl.handle.net/20.500.11984/14628 Replica-Based Moving Target Defense Against Injection Attacks in Software-Defined Industrial Control Systems Etxezarreta, Xabier; Turrin, Federico; Garitano, Iñaki; Iturbe, Mikel; Zurutuza, Urko; Conti, Mauro Recent incidents have demonstrated the increasing vulnerability of Industrial Control Systems (ICSs) to sophisticated and targeted attacks orchestrated by adversaries with high motivation, resources, and domain knowledge. Among these threats, False Data Injection (FDI) attacks have emerged as one of the main security threats to ICSs, involving the deliberate manipulation or injection of false data into the control system to deceive or disrupt operations. FDI attacks pose a significant risk due to their high capacity of concealment and ability to evade intrusion detection systems that rely on accurate ICS models. In this paper, we present defclon, a novel Software-Defined Networking (SDN)-based Moving Target Defense (MTD) approach against FDI attacks. Defclon proactively replicates network packets across multiple network paths and adaptively selects a single path using a signaling game model to reach the destination end-device. We demonstrate the effectiveness of our approach through simulations, numerical analysis, and experiments on ICS network traffic and topologies. Experimental results show that defclon is able to not only mitigate the effects of FDI attacks, but also to introduce different levels of uncertainty without degrading network performance, significantly increasing the difficulty for adversaries to gather information and launch attacks. Thu, 01 Jan 2026 00:00:00 GMT https://hdl.handle.net/20.500.11984/14628 2026-01-01T00:00:00Z https://hdl.handle.net/20.500.11984/14627 Explainable and Evaluative Artificial Intelligence: Alternatives to Ensure Equity in Decision-Making Villuendas Rey, Yenny; Camacho-Nieto, OSCAR; Tusell Rey, Claudia; Salinas García, Viridiana ; Pino Gómez, Joel Explainable Artificial Intelligence (XAI) and Evaluative Artificial Intelligence (EAI) are crucial approaches to ensuring fairness in decision-making. XAI refers to the ability of Artificial Intelligence (AI) systems to be understood and explained by humans, while EAI is a new paradigm that focuses on identifying possible decisions for intelligent algorithms by formulating hypotheses for and against them. Thu, 01 Jan 2026 00:00:00 GMT https://hdl.handle.net/20.500.11984/14627 2026-01-01T00:00:00Z https://hdl.handle.net/20.500.11984/14626 A Probabilistic Physics-Aware Battery Health Management Approach for Inspection Drone Operations Alcibar, Jokin; Aguirre, Aitor; Aizpurua Unanue, Jose Ignacio The increasing deployment of inspection drones for monitoring remote and critical infrastructure presents new opportunities and challenges in asset management. These drones operate in demanding environments, where ensuring operational reliability is essential. Among the various subsystems, battery health plays a central role in determining mission success and safety. This chapter presents a physics-aware probabilistic approach for battery health management, integrating data-driven techniques with physics-based models to improve the predictability of battery performance. At the core of this methodology lies a probabilistic machine learning model that provides uncertainty quantification, enabling more informed and robust decision-making. By incorporating this uncertainty-aware perspective into battery discharge forecasting, the approach supports advanced digital maintenance strategies. The methodology is demonstrated to drone-based inspections of offshore wind energy infrastructure, highlighting its contribution to enhancing asset reliability and enabling condition-aware maintenance strategies. Thu, 01 Jan 2026 00:00:00 GMT https://hdl.handle.net/20.500.11984/14626 2026-01-01T00:00:00Z https://hdl.handle.net/20.500.11984/14625 Sow Smarter, Not Harder: Evaluating LLM-Generated Seeds for Fuzzing Critical Infrastructure Barredo Ferreira, Jorge; Eceiza, Maialen; Flores, Jose Luis; Iturbe Urretxa, Mikel Software vulnerabilities in critical infrastructure components can lead to severe disruptions. While fuzzing effectively identifies such weaknesses, the quality of initial seed inputs significantly impacts its effectiveness. This study evaluates how large language models (LLMs) can generate better fuzzing seeds for critical infrastructure software. We compared seven LLMs—ChatGPT-4-Turbo, Claude 3.0 Opus, Claude 3.7 Sonnet, DeepSeek-V3, Gemini 2.0 Flash, Grok 3, and Mistral 7B—with manual baselines across six programs, including industrial control libraries, routing components, and network firmware. Over 20 independent 24-h campaigns per model and program, LLM-generated seeds achieved 14.8% higher code coverage, detected 56.3% more unique crashes, and reached first crashes 373.9% faster than manual methods. Performance patterns emerged across different infrastructure protocols, with certain models excelling at complex SCADA data formats while others performed better for network security components. The 56.5% computational efficiency improvement benefits resource-constrained operational technology environments. These findings demonstrate that LLM-generated seeds can meaningfully enhance vulnerability detection in software underlying critical infrastructure systems, offering a practical approach to strengthening resilience against cyber threats . Thu, 01 Jan 2026 00:00:00 GMT https://hdl.handle.net/20.500.11984/14625 2026-01-01T00:00:00Z