British University Vietnam

The transition to 6G and Open RAN (O-RAN) necessitates intelligent orchestration across multi-operator networks, yet this collaboration introduces severe security and privacy risks. Malicious operators may poison global models through adaptive attacks, while the exchange of raw gradients threatens data sovereignty. In this paper, we propose FORTRESS-FL , a robust and privacy-preserving federated learning framework designed for secure cross-domain orchestration. At its core is the TrustChain protocol, which synergizes a commit-then-reveal scheme to prevent adaptive manipulation, unsupervised spectral clustering for Byzantine detection, and a dynamic reputation system to isolate malicious actors. Furthermore, we integrate an adaptive Differential Privacy (DP) mechanism to rigorously protect operator data. Extensive evaluation on a real-world financial fraud dataset demonstrates that FORTRESS-FL achieves 100% detection accuracy against sign-flip attacks with 30% Byzantine adversaries, preventing the model divergence observed in standard baselines. Scalability tests confirm linear complexity with respect to the number of operators, validating the framework’s feasibility for large-scale, real-time network orchestration.

This study explores online deliberation and discursive (in)civility within Vietnam’s authoritarian context, focusing on Facebook discourse during the COVID-19 pandemic. It examines how different types of Facebook pages (i.e. government information pages, state-sponsored media, foreign media, and private discussion groups) shape deliberative quality and how (in)civility can both facilitate and hinder public discussion. Quantitative analysis reveals that foreign media pages foster more rational, diverse, reflexive, and interactive discussions, despite higher levels of incivility. In contrast, government and state-sponsored media pages maintain greater civility but demonstrate lower deliberative quality, while private groups show high incivility with minimal deliberation. To further contextualize these patterns, a close reading identifies emotional triggers and target-induced behaviors in uncivil comments. By integrating macro-level metrics with micro-level discursive practices, this study offers valuable insights for scholars and policymakers seeking to enhance deliberative engagement in digital environments under varying degrees of state control.

Accurate prediction of individual treatment effects in survival analysis is often complicated by the presence of competing risks and the inherent unobservability of counterfactual outcomes. While machine learning models offer improved discriminative power, they typically lack rigorous guarantees for uncertainty quantification, which are essential for safety-critical clinical decision-making. In this paper, we introduce CONFIDE (CONFormal Inference for Distribution-free Estimation), a novel framework that bridges causal inference and conformal prediction to construct valid prediction sets for cause-specific cumulative incidence functions. Unlike traditional confidence intervals for population-level parameters, CONFIDE provides individual-level prediction sets for time-to-event outcomes, which are more clinically actionable for personalized treatment decisions by directly quantifying uncertainty in future patient outcomes rather than uncertainty in population averages. By integrating semi-parametric hazard estimation with targeted bias correction strategies, CONFIDE generates calibrated prediction sets that cover the true potential outcome with a user-specified probability, irrespective of the underlying data distribution. We empirically validate our approach on four diverse medical datasets, demonstrating that CONFIDE achieves competitive discrimination (C-index up to 0.83) while providing robust finite-sample marginal coverage guarantees (e.g., 85.7% coverage on the Bone Marrow Transplant dataset). We note two key limitations: (1) coverage may degrade under heavy censoring (>40%) unless inverse probability of censoring weighted (IPCW) conformal quantiles are used, as demonstrated in our sensitivity analysis; (2) while the method guarantees marginal coverage averaged over the covariate distribution, conditional coverage for specific covariate values is theoretically impossible without structural assumptions, though practical approximations via locally-adaptive calibration can improve conditional performance. Our framework effectively enables trustworthy personalized risk assessment in complex survival settings.

Public WiFi networks deployed across high-density transit environments — such as train stations, bus terminals, and airports — present a largely unaddressed frontier in network intrusion detection research. These venues collectively serve tens of millions of users monthly yet exhibit extreme traffic heterogeneity, continuous attack pattern drift, and strict data privacy constraints that preclude centralized detection paradigms. Existing federated learning-based intrusion detection systems (FL-IDS) fail to simultaneously address the spatiotemporal dynamics of evolving network topologies, the interpretability requirements of operational security teams, the concept drift inherent to live deployments, and the fairness disparities that arise across heterogeneous venue types. We propose ST-FedXIDS, a Spatiotemporal Federated Explainable Intrusion Detection System that unifies five technical contributions: (1) a heterogeneous dynamic graph construction pipeline that models multi-protocol WiFi traffic as sliding temporal-window graphs; (2) ST-GraphSAGE with multi-head temporal self-attention, replacing the LSTM/GRU paradigm used in all prior spatiotemporal GNN-IDS works; (3) Drift-Adaptive Federated Averaging (DA-FedAvg) that embeds ADWIN-based graph embedding drift detection directly into the federated aggregation protocol; (4) a GNN-Explainer module that produces subgraph-level attack attribution explanations for operational incident response; and (5) a venue-type fairness regularizer that minimizes the maximum inter-venue false positive rate gap across heterogeneous deployment sites. Extensive experiments on three public benchmarks — CSE-CIC-IDS2018, TON_IoT, and UNSW-NB15 — against four 2025 state-of-the-art baselines demonstrate that ST-FedXIDS achieves 98.21%–99.13% accuracy, outperforming all competitors by 0.9–2.4 percentage points, reduces the inter-venue FPR gap from 8.5–12.3% to 2.1%, and recovers from concept drift in 8 federation rounds versus 19–25 rounds for competing methods. An ablation study validates the independent contribution of each component.

Purpose Recent advances in generative AI (GenAI) are transforming multiple aspects of society, including education and foreign language learning. In the context of English as a Foreign Language (EFL), significant research has been conducted to investigate the applicability of GenAI as a learning aid and the potential negative impacts of these technologies. However, there are few formalised frameworks available to support the integration and development of AI literacy skills for EFL learners. Design/methodology/approach In this conceptual article, we demonstrate the way in which an existing framework, which is designed for integration of AI into educational assessment (the AI Assessment Scale), can be adapted to structure classroom activities, curricula and assessment in the context of EFL writing and translation. To achieve this, we contextualise the approach by firstly reviewing the extant literature on GenAI and EFL writing. Following this, we focus on Levels 2, 3 and 4 of the AI Assessment Scale (AIAS) and explore possible pedagogical adaptations to suit an EFL writing context. At the same time, we reflect on the possible advantages and limitations of this approach. Findings We argue that for pedagogy to succeed in a digital world, educators in the EFL field must not turn away from the affordances offered by AI technologies. At the same time, abundant caution is needed given the lack of empirical data on how these technologies may impact learning in the long term. To this end, we contend that a balanced approach, which clearly describes and communicates how AI may be used in learning activities, can be beneficial for both educators and learners in the EFL classroom. Practical classroom implications are included for writing and translation so teachers can apply the patterns immediately. Originality/value The adaptation of the AIAS from an assessment redesign tool to a framework for structuring EFL pedagogy is the core contribution and innovation in this article. The use of this framework has significant implications for classroom practice in the age of AI, as it enables a structured redesign of existing pedagogical activities in light of new technologies.

Preventing children online is the herculean task when there is no proper information about the children to whom they connect. As online predators hide their age and profile on social media through their villainous tactics and communication with adolescents. It is highly unlikely to say which application and tools can detect their age and profile easily. It is essential to ensure the offender's age on social media platforms and identifying the offenders online. This article addresses detecting the issues related to online child abuse with the help of federated learning. A promising technology emerges to address these issues effectively. The federated learning approach for early detection of sexual predators helps to preserve the privacy issues of victims. The article also focuses on the research gaps to identify, detect, and analyze the offender's false profile that shows their age and gender and shows the intense knowledge about the federated learning approach to tackle this societal issue.

Any unattended baggage in public stations is believed to be considered as a threat to citizens. Fortunately, identification of such objects is one of computer vision problem which can be solved by AI and ML algorithm. Therefore, the need for accuracy and real-time application to increase safety in public places such as airports, train stations is mandatory. The chapter explores an automated framework of unattended baggage detection for video surveillance, and the stages of developing an algorithm. The various methods of performing data processing and feature selection are highlighted in this literature review.

In the current digital transformation era and e-commerce, recommendation systems (RS) have become vital in optimizing profits and finding and reaching potential customers. Large companies (Facebook, Google, Amazon, etc.) possess huge amounts of data about customers and goods and it is important to exploit information to create customer suggestion systems. Suitable products will improve customer experience, save advertising costs, and sell more products. Therefore, it will make huge profits from marketing and e-commerce. This paper aims to build and optimize popular models for the problem of RS on the MovieLens dataset. Therefore, we test and compare the capabilities predictions of these types of models. In addition, this project uses PySpark technology to increase the amount of data aiming for execution on large datasets in practice to evaluate how the amount of data affects the ability to suggest. We also present the models and the construction installation steps environment and optimize their parameters. We assess each algorithm on the Movielens 100k and 1M. The results show that the model has MAE as 81.21% and 87.47% on two datasets Movielens 100k and 20M.