2026.08.03Preprint (HAL) presenting OTARQ, an automated framework that quantifies cybersecurity, safety, and fleet risk for Over-The-Air updates on Software-Defined Vehicles.
2026.05.18Paper presented at IEEE/IFIP NOMS 2026 (MCT workshop) on a graph-based approach (GPML) for detecting cyberattacks in water distribution networks from topology changes.
Paper presented at EvoApplications 2026 (Toulouse) on an evolutionary-ML approach building lightweight probabilistic surrogates for cyber-attack detection on edge devices in Water Distribution Networks.
Paper presented at KES 2025 (Osaka) defining t-robustness and a feature engineering approach, evaluated on UGR16 enriched with graph community metrics, that produces attack-detection models more stable under concept drift.
2025.09.01Journal article (SoftwareX) presenting GPML, an open-source library that transforms raw network traffic into graph representations for community and spectral-metric-based cyberattack detection.
2025.08.01RedTeamLLM is an integrated agentic AI architecture for automating pentest tasks, following a summarize/reason/act loop, evaluated on entry-level CTF challenges.
2024.07.30Paper presented at ARES 2024 (Vienna) introducing SpectraTW, a spectral graph analysis methodology using four spectral indicators to detect cyberattacks from network topology, with a focus on medical IoT.
2024.07.01Paper presented at WDSA/CCWI 2024 (Ferrara) providing a multi-layer machine-learning approach that combines physical and network traffic data, assessing its effect on attack-detection performance and its cross-impact with graph-metric-enriched data.