Authors - Ali Fenjan, Mohammed Almulla, Jalil Md Desa Abstract - Android malware detection datasets are commonly designed for classification accuracy, while their ability to support explainability, forensic interpretation, and analyst-driven security reasoning remains limited. This paper presents APU-Android, an explainable static–behaviour feature dataset for An-droid malware forensics and security analytics. The dataset contains 4,594 APK records; after duplicate removal, 4,281 cleaned records were used in the strict evaluation. APU-Android represents each APK using nine interpretable features: requested permissions, API calls, file size, encryption usage, obfuscation level, network requests, suspicious keywords, network-risk flag, and Behaviour Score. Unlike opaque high-dimensional representations, each feature is mapped to a security-relevant meaning, allowing model decisions to be interpreted in terms of privilege abuse, API capability, concealment, communication risk, suspicious string evidence, and behavioural risk. The evaluation excluded du-plicated normalized columns, applied group-aware splitting using App_Name, and benchmarked five machine-learning classifiers. Under group-aware evaluation, Extra Trees achieved 98.72% accuracy, 99.38% precision, 98.37% recall, 98.87% F1-score, and 99.84% ROC-AUC using only the nine original explain-able features. Ablation analysis further examined the role of Behaviour Score and Obfuscation Level, while SHAP analysis showed that Network_Requests, API_Calls, and Permissions_Requested were the most influential prediction features. The results demonstrate that APU-Android is not only classification-ready, but also explanation-ready and forensic-ready for Android malware security analytics.
Authors - Senaya Nurandhi Jayawickrama, Tithira Mojitha Ranasingha, Dineth Randika Kumaranayake, Udageeth Dias, Kavinga Yapa Abeywardena, Amila Nuwan Senarathne Abstract - The increased digitization of banking operations has increased the value of data assets while also exposing them to growing cyber risks, creating a need for effective risk management mechanisms. Cyber insurance is a risk transfer mechanism that enables organizations to mitigate financial losses by transferring cyber risks to third party insurers. However, in many emerging markets, including Sri Lanka, cyber insurance remains underdeveloped due to limitations in existing premium calculation models, as they lack transparency and fail to incorporate data asset valuation and relevant security parameters, resulting in inaccurate and unfair premiums. This study proposes a structured framework that integrates data asset valuation with premium calculation, while defining multiple insurance coverage categories to address financial losses arising from regulatory, operational and recovery risks. By incorporating data asset value, operational criticality and organizational security posture into the premium calculation process, the proposed models enhance the accuracy and fairness of premium values.
Authors - Nguyen Ngoc-Tuan, Nguyen Van-Giap Abstract - Blended learning (BL) has played an important role in the improvement of learners. The special features of BL are useful for teachers and students, such as various learning contents, personal learning activities, and the mechanism related to authentic learning. However, the BL influences for different major students should be carefully studied and will contribute to the community. This study investigates the influences of BL based on a blended learning system (BLS) on university students’ achievement in different majors. Based on 247 courses in two years (2023 and 2024), without and with the BLS, we gathered and analysed the learning achievements of more than 9000 students from different majors stud-ying at a university. We also categorised the students into two main majors, in-cluding social science (SSCI) majors and engineering majors (SCI). Learning based on the system, the learning achievement of SSCI students is significantly higher than that of SCI students. We also found that the BLS improved the learning scores of the good students learning in both SSCI and SCI majors. Addition-ally, the SSCI students’ scores were significantly higher than those of the SCI students. The direction in the skills assessment of the SCI majors may be the main cause of the differences in university educational settings. Several suggestions on how to attract the low-scoring students to learn actively with BLS were also given. The important findings can contribute to the community to develop and apply blended learning for the different university major contexts.
Authors - Janitha Prabodha Bandara Dissanayaka, Pumudu A. Fernando, Manul Randula Singhe Abstract - Three-dimensional scene representation has moved quickly from Neural Radiance Fields (NeRF) to explicit volumetric methods such as 3D Gaussian Splatting (3DGS). 3DGS can render photorealistic scenes in real time, but editing these scenes is still difficult because Gaussian primitives do not have a fixed mesh structure or explicit topology. This becomes more challenging in dynamic scenes, where edits must remain stable across time and viewpoint. This paper presents a systematic literature review of neural volumetric editing methods for dynamic 3DGS and related NeRF-based representations. The review follows a PRISMA-guided process and analyses studies published between 2023 and 2026. The selected methods are grouped into three main paradigms: text-guided editing, interaction-based editing, and physics-based simulation. The review compares these methods using control precision, rendering speed, memory usage, editing time, temporal stability, and practical limitations. The findings show that text-guided methods are easy to use but often suffer from weak localisation and temporal inconsistency. Interaction-based methods provide stronger geometric control but struggle with complex topology changes. Physics-based methods produce more realistic motion but require higher computation and reliable material parameters. The review identifies the consistency gap, including flickering and texture swimming, as the main barrier to real-world dynamic neural volumetric editing.
Authors - Mazin Alshamrani Abstract - Wearable physiological monitoring systems are increasingly deployed in health-critical contexts, yet existing approaches address state classification, transition detection, and signal safety as isolated problems. This paper introduces SafeWear, a unified signal quality-aware machine learning framework that jointly addresses (i) real-time and anticipatory detection of physiological state transitions, and (ii) multimodal anomaly detection and out-of-distribution (OOD) safety screening. The framework centres on a modality-level Signal Quality Index (SQI) acting as a front-end reliability gate distinguishing sensor-level failures from genuine physiological irregularities. Causal temporal models are evaluated for transition detection, while reconstruction-based and one-class detectors are benchmarked for anomaly safety under strict Leave-One-Subject-Out Cross-Validation (LOSO-CV) across 37 subjects and five wearable modalities. Preliminary results show causal models achieve median detection latencies below 5.2 s with early-detection rates exceeding 79%, and Deep SVDD with VAE yield the strongest anomaly discrimination (AUROC = 0.539 and 0.538).
Authors - Hoang Anh Tuan, Le Thien Nhi Abstract - As governments digitize public services, educational platforms have emerged as essential e-governance infrastructure managing users’ personal and academic data. Vietnam’s National Digital Transformation Program enforces higher education digitalization as a strategic priority, but how users’ perceive the security of these systems, and whether such perceptions translate into trust, remains underexplored. This study review literature linking Perceived Information Security Assurance, Perceived Information Security Risk, Trust, Intention to Use, and Intention to Share Personal Information among university students in Hanoi and Ho Chi Minh City. Drawing on the Technology Acceptance Model, Protection Motivation Theory, and the CIA triad, the review proposed that security assurance strongly predicts trust, and trust drives both usage intention and willingness to share personal data. Contrary to expectations, perceived risk does not diminish trust but coexists with continuous platform use. As artificial intelligence features become more standardized in educational e-governance, these trust dynamics gain urgency as citizens or users must trust not only data handling but algorithmic/AI decision-making. The review synthesizes evidence from e-government adoption, educational systems and AI governance literatures to understand trust formation in AI-enhanced educational e-governance, with implications for platform design, policy development, and future research addressing accountability and e-governance in educational contexts.
