Unmanned Aerial Vehicles (UAVs) serve an essential function in various civilian, commercial, and military applications, but their reliance on wireless communication, onboard sensors, and ground control systems make them vulnerable to a comprehensive set of cyber threats. Existing security measures—ranging from cryptographic protocols to traditional intrusion detection—struggle to address evolving attack vectors such as GPS spoofing, man-in-the-middle (MITM), jamming, denial-of-service/distributed-denial-of-service (DoS/DDoS), and other advanced UAV-specific intrusions. This study proposes a lightweight ensemble machine learning framework integrating Light Gradient Boosting (LightGBM), Histogram-based Gradient Boosting (HGB), and Categorical Boosting (CatBoost) to detect both sensor-based and broader cyber-attack types in UAV environments. To enhance trust and operational transparency, Explainable AI (XAI) is embedded into the framework, enabling interpretability of detection outcomes for operators and stakeholders. The proposed model is evaluated on the UAV-GCS-IDS dataset capturing diverse attacks, including DoS/DDoS, brute force, reconnaissance, scanning, MITM, replay, fake landing, and evil twin intrusions. Results from the experiments indicate that the ensemble surpasses baseline machine learning models with 99.74% accuracy, 99.87% F1-score, 99.86% precision, and 99.88% recall. In addition, the model also achieves a robust ROC-AUC of 99.85% and PR-AUC of 100.0%, while maintaining low computational overhead—making it suitable for resource-constrained UAV systems. This work strengthens UAV cybersecurity by introducing an interpretable, high-performance detection framework capable of operating effectively in realworld, mission-critical scenarios.
C. Chidimma, P. Asuquo, Ihemereze Chijioke Nnanna et al.· E3S Web of Conferences· 0 citations
Financial fraud detection in transaction networks is challenging due to evolving attack strategies, complex relational structures, and extreme class imbalance. We propose a hybrid deep learning model that fuses Graph Convolutional Neural Networks (GCNNs) with bidirectional LSTMs enhanced by temporal attention, enabling joint modeling of structural dependencies and sequential transaction patterns. To improve class discrimination, the framework incorporates Triplet Loss, enhancing prior contrastive approaches, which enhances embedding separability under highly imbalanced conditions. Furthermore, we introduce graph augmentation strategies, including edge perturbation, node feature masking, and adaptive subgraph sampling, to increase robustness against noise and incomplete networks. Experiments on the IEEE-CIS and synthetic datasets with varied patterns demonstrate that the proposed model achieves up to 6.2% improvement in F1-score with a modest precision-recall trade-off favoring high-recall scenarios and 12% higher recall compared to strong baselines. Ablation studies confirm the complementary roles of the graph, temporal, and metric learning components. These consistent improvements, demonstrate that incorporating Triplet Loss within graph–temporal modeling provides a principled and effective approach to imbalanced fraud detection, establishing our model as a scalable and robust solution for fraud detection in financial transaction networks.
Ofonime Dominic Okon, Imo Enang, B. Stephen et al.· E3S Web of Conferences· 0 citations
Industrial control systems (ICSs) are the operational technology that monitors and directs physical processes across critical infrastructure. They sit at the core of Industry 4.0. Once these systems are connected to digital platforms and service chains, a flaw in one component is no longer confined to that component. Conventional practice still treats disclosed vulnerabilities as isolated events to be patched, which leaves an open question: does the way vulnerabilities accumulate across ICS infrastructure amount to systemic risk, a property of the system rather than of any single flaw? We examine this using the ICS-CERT Vulnerability Dataset, analysing 60,378 vulnerability-product records that cover 2327 unique Common Vulnerabilities and Exposures (CVE) entries, 416 vendors and 14,577 affected products from 2012 to 2020. We construct a System Risk Index (SRI) that aggregates vulnerabilities to the vendor-year level, weighted by severity and exploitability. An ordinary least squares (OLS) model with heteroscedasticity-robust standard errors explains vulnerability severity (R2 = 0.99). A second model explains system-level risk (R2 = 0.91). Vulnerability-type diversity, measured through the Common Weakness Enumeration (CWE) taxonomy, is the strongest driver of SRI (β = 1.25, p < 0.001), ahead of mean exploitability (β = 0.29, p < 0.001) and product breadth (β = 0.06, p = 0.001). Annual ICS disclosures rose from 115 in 2012 to 503 in 2019, an increase of 337 per cent. Risk is concentrated: the five largest vendors account for 33.3 per cent of disclosed CVEs and more than 60 per cent of the cumulative SRI, with one vendor carrying over twice the cumulative SRI of the next. Quantile regression confirms the severity findings at the median. The pattern indicates that digital transformation redistributes risk into a connected, vendor-level property of the infrastructure beneath product–service delivery. Oversight should therefore track the diversity and exploitability of a vendor’s vulnerabilities rather than severity alone, concentrating scrutiny on the small set of vendors that carry most of the systemic exposure.
Imo Enang, Iniobong Enang, I. Akpan· Systems· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
