Abstract
We present a federated edge-intelligence framework for smart-mobility cybersecurity that integrates Edge AI, Federated Learning (FL), and blockchain anchoring, and we provide a runnable artifact for full reproducibility. Using a synthetic IDS-like workload with non-IID client splits, we benchmark centralised, edge-only, and FL (FedAvg) training while accounting for communication, a latency proxy, and a FLOPs-based energy index. FL maintained near-centralised accuracy (˜99.8%) and F1 (0.9932–0.9938), whereas edge-only degraded under client skew (˜85.3% accuracy; F1 ˜ 0). Training-time communication for FL was 98.96% lower than centralised at 5 clients/10 rounds (0.033 MB vs. 3.206 MB) and 97.99% lower at 10 clients/10 rounds (0.065 MB vs. 3.206 MB). The latency proxy grows linearly with FL rounds yet remains well below centralised inference (132 ms vs. 3,301 ms at 5 clients/10 rounds). Energy results follow expectations: edge-only lowest (0.000832), centralised mid (0.001040), and FL highest due to local training (0.001300–0.001560). Overall, the results quantify accuracy/communication/latency/energy trade-offs and show that federated-edge learning preserves accuracy under client heterogeneity while minimizing raw-data transfer; blockchain anchoring adds only a small, parameterized per-commit overhead. All configurations and logs are released to enable exact reproduction. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Abstract
Detection of leaks in hydrogen (H2) infrastructure is required on a large scale to enable a safe widespread use of this clean energy source. Sensing solutions must be low-cost, use scalable fabrication methods and allow multiplexed detection, while providing reliable safety alarms as fast as possible. Optical methods can make this possible while avoiding the risk of ignition due to electronics at the point of detection. Metal hydride-based micro-mirror configurations benefit from a simple interrogation scheme, as long as the sensitive element can produce a large optical response. Magnesium thin films undergo a drastic variation of properties when hydrogenated, making them suitable for this application. In this work, a micro-mirror device using single-mode fibers capable of detecting the presence of H2 with a loading t10 and t90 of 1.2 and 3.0 seconds, respectively, is demonstrated. A complete interrogation unit was developed, presenting a solution suited for widespread deployment using industry-standard optical components and equipment.

Abstract
This study examines whether Parameter-Efficient Fine-Tuning (PEFT) of lightweight, free, and open-licensed Large Language Models (LLMs) can yield tutoring assistants for introductory circuit analysis methods, while fitting the students' needs. We analyzed 260 Electrical and Computer Engineering (ECE) exam responses to classify and quantify frequent students' mistakes when applying the Loop Current Method (LCM). Only 28.5% solved the target problem without error, and most difficulties were conceptual (e.g., miscounting the number of independent Kirchhoff's Voltage Law (KVL) equations). Driven by this taxonomy, we assembled official course materials and curated a bilingual (Portuguese-English) pedagogical dataset. Using GTP-4o for distillation, we generated question-answer (QA) pairs for fine-tuning smaller models (Meta Llama 3.2 1B and 3.1 8B), via Quantized Low-Rank Adaptation (QLoRA) on a single commodity GPU, with an end-to-end pipeline completing in under 7 min. A blind study involving 77 first-year ECE students evaluated responses to (never seen) questions from both our tuned models and GPT-4.5, rating correctness, clarity, educational value, task coverage, and style. The 8B model scored within one point (5-point Likert) of GPT-4.5 model and both 1B and 8B were consistently preferred over untuned baseline versions for clarity and task coverage. As a complementary cross-check, 12 higher education senior professors independently evaluated model responses, largely corroborating the student-based rankings. These results provide evidence that carefully curated documents introducing electrical circuit theory, combined with smaller models optimized with PEFT, namely QLoRA, can be used in the construction of a always-available tutoring application. The proposed system features modest cost, runs on consumer-grade hardware, and paves the way for deployable front-end applications that do not involve possibly expensive, resource-hungry, remote machines.

Abstract
This study proposes a two-stage Intrusion Detection System (IDS) for Controller Area Networks (CAN) that leverages protocol-specific timing characteristics. Modern vehicular networks are vulnerable to injection attacks due to the CAN protocol's lack of built-in authentication. Our methodology transforms raw CAN traffic into a structured feature space consisting of CAN IDs, message offsets, and inter-message intervals derived from the CAN Remote Frame request-response mechanism. The first stage applies unsupervised z-score statistical thresholding, requiring no labeled attack data. The second stage employs three independent binary Random Forest (RF) classifiers for precise characterization. Individual classifiers achieve F1-scores of 0.96 (Fuzzy), 0.77 (DoS), and 0.79 (Impersonation). In the integrated end-to-end pipeline, while the system effectively filters 97% of legitimate traffic, a performance stratification is observed: high detection is maintained for timing-disruptive attacks (Fuzzy), whereas timing-preserving attacks (DoS, Impersonation) exhibit lower recall due to the restrictive nature of the timing-only first-stage gating mechanism. Hardware profiling confirmed an inference latency of similar to 0.018 ms and footprint of 8.8-19.2 MB, offering a deployable, computationally efficient defense for legacy automotive environments.

Abstract
Machine Learning (ML) has emerged as a promising technique to make detection tools more accurate and adaptable to the ever-evolving, increasingly voluminous threat of ransomware attacks. In this paper, we study MLbased ransomware detection solutions grounded in behavioral analysis, from the perspective of reproducibility and replicability, as these properties are key for validating, reusing, and comparing existing work. Our study explores how these properties evolved over the past 10 years for the full ML pipeline workflow (i.e., sample collection and analysis, feature extraction/selection, model configuration, and explainability). We discuss often overlooked yet critical challenges and provide guidelines to improve reproducibility and replicability in the field. © 2026 IEEE.

Abstract
A point-of-care test (POCT) based on low-cost and highly sensitive disposable chips was designed for the sensitive and selective detection of proteins. In particular, a pollen-based plasmonic nanostructured probe coupled, for the first time, with biomimetic receptors custom-designed as molecularly imprinted nanoparticles (MIP-NPs) for protein recognition, was developed and interrogated by an extrinsic optical fiber (OF)-based scheme. To this purpose, bovine serum albumin (BSA) was chosen in a proof-of-concept frame as an example of a protein. (c) 2026 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement