Luminous defense: XAI-driven adaptive security for critical IoT infrastructures

Imposter devices pose serious threats. The majority of low-cost edge devices can easily be counterfeited or cloned; the supply chain is insufficiently secure. Reliability of deployed devices can be called into question simply because they might be counterfeit or cloned. It is a must to identify edge devices' sourcing uniquely and verify their validity periodically at runtime. We integrate blockchain technology to authenticate resource-constrained, low-cost edge devices. We use SRAM-based physically unclonable functions (PUFs)to generate unique “digital fingerprints” (device IDs). Registered manufacturers upload a cryptographic hash of each device ID to a “globally accessible” blockchain instance (key-value store or smart contract). While registering/designating a device locally, the end-user verifies whether the hash is present in that blockchain. We utilize a “locally permissioned” blockchain infrastructure (which is still a globally managed blockchain or, in future, a sidechain)to authenticate edge devices for a defense-in-depth approach. Devices can authenticated periodically to prevent device cloning. Target environments can be large and have varied trust among users and lack a specific perimeter; this “local” blockchain methodology is thus pertinent, especially since blockchains gain security over time. Our approach reduces the potential for classes of information leakage and types of sabotage in a critical infrastructure or large-scale deployment (such as a smart city)arising from imposter devices. This methodology protects against such imposters in mobile settings within an IoT infrastructure too.

Multisensor networks are widely used for monitoring in industrial IoT and critical infrastructure. In complex spatiotemporal and dynamic environments they face two main challenges. First, fusing high-dimensional multimodal data is difficult. Second, frequent sensor-topology changes hinder dynamic graph modeling. Traditional static-graph methods cannot capture complex dynamic interactions, and deep fusion models are computationally heavy and often lack interpretable anomaly explanations. To address these issues, we propose the DGM-PIIoT framework. It incrementally updates the sensor graph with a time-aware GNN and uses a multimodal attention mechanism to jointly model spatial, temporal, and topological features of heterogeneous sensors. Experiments on an industrial pump-station dataset show significant improvement in anomaly detection performance (F1-score 92.70%) over existing methods.

This research addresses the pressing challenge of intrusion detection and prevention in Wireless Sensor Networks (WSNs), offering an innovative and comprehensive approach. The research leverages Support Vector Regression (SVR) models to predict the number of barriers necessary for effective intrusion detection and prevention while optimising their strategic placement. The paper employs the Ant Colony Optimization (ACO) algorithm to enhance the precision of barrier placement and resource allocation. The integrated approach combines SVR predictive modelling with ACO-based optimisation, contributing to advancing adaptive security solutions for WSNs. Feature ranking highlights the critical influence of barrier count attributes, and regularisation techniques are applied to enhance model robustness. Importantly, the results reveal substantial percentage improvements in model accuracy metrics: a 4835.71% reduction in Mean Squared Error (MSE) for ACO-SVR1, an 862.08% improvement in Mean Absolute Error (MAE) for ACO-SVR1, and an 86.29% enhancement in R-squared (R2) for ACO-SVR1. ACO-SVR2 has a 2202.85% reduction in MSE, a 733.98% improvement in MAE, and a 54.03% enhancement in R-squared. These considerable improvements verify the method's effectiveness in enhancing WSNs, ensuring reliability and resilience in critical infrastructure. The paper concludes with a performance comparison and emphasises the remarkable efficacy of regularisation. It also underscores the practicality of precise barrier count estimation and optimised barrier placement, enhancing the security and resilience of WSNs against potential threats.

Database and system security are critical components in modern information technology, underpinning the reliability and trustworthiness of digital services. With the proliferation of cloud computing, Internet of Things (IoT) devices, and mobile platforms, the attack surface for cyber threats has expanded significantly, creating challenges for confidentiality, integrity, and availability of data. This paper provides a comprehensive review of contemporary database and system security concepts, including access control models, encryption techniques, intrusion detection, and auditing practices. Emerging threats such as ransomware, supply chain attacks, and insider threats are analyzed, alongside mitigation strategies including artificial intelligence (AI)-driven monitoring, blockchain-based integrity verification, and quantum-resistant cryptography. Through case studies in healthcare, finance, and critical infrastructure, the paper highlights practical applications and challenges of security implementation. Finally, it identifies future directions in adaptive security frameworks, zero trust architectures, and privacy-preserving computation, emphasizing the need for a proactive and resilient approach to securing databases and systems.

A wireless network composed of UAVs collaborating to upload data to the inter-net is known as a swarm of unmanned aerial vehicles (S-UAVs). UAVs are utilized extensively to convey important data during emergency situations like earthquakes or floods. Clustering, which divides the network into clusters with a cluster head (CH) and cluster members (CM), is one of the most dependable routing strategies in S-UAVs. A disconnected cluster and loss of data are the result of a damaged or non-functional CH, which is a topic that is rarely explored. This work proposes an improved multiple redundant routing strategy based on three weighted parameters: energy, rewarding, and propagation delay for reliable data transmission through ensuring a functional CH. This paper exclusively uses the coefficient of variation to set the weights used in the weighted calculation that generates a new parameter denoted as cluster index. Based on the cluster index, the nodes are selected as CH or CMs, thus forming the clusters. To decrease the probability of non-functional CH, we propose the cooperation of different types 1 of agents, which are vehicles and UAVs in our case. Having different types of agents will increase the system’s reliability, as the risk of non-functionality in a crisis scenario depends highly on the agent’s type. To ensure a functional CH, a redundant CH is selected to take over the routing duties to ensure connection stability. Every node has a redundant node selected which ensures that despite the number of non-functional nodes a functional CH still exists. MATLAB was used to simulate the suggested routing scheme. The outcomes showed that our suggested scheme holds promises for lowering overall latency and guaranteeing a functional CH, thus successful data delivery with minimal delays.

The growing demand for IoT devices is accelerating the pace of their production. In an effort to accelerate the launch of a new device and reduce its cost, manufacturers often neglect to comply with cybersecurity requirements for these devices. The lack of security updates and transparency regarding the security status of IoT devices, as well as unsafe deployment on the Internet, makes IoT devices the target of cybercrime attacks. Quarterly reports from cybersecurity companies show a low level of security of the Internet of Things infrastructure. Considering the widespread use of IoT devices not only in the private sector but also in objects for various purposes, including critical infrastructure objects, the security of these devices and the IoT infrastructure becomes more important. 
 Nowadays, there are many different methods of detecting cyberattacks on the Internet of Things infrastructure. Advantages of applying the machine-based methods in comparison with signature analysis are the higher detection accuracy and fewer false positive, the possibility of detecting both anomalies and new features of attacks. However, these methods also have certain disadvantages. Among them there is the need for additional hardware resources and lower data processing speeds. The paper presents an overview of modern methods aimed at detecting cyberattacks and anomalies in the Internet of Things using machine learning methods. The main disadvantages of the known methods are the inability to detect and adaptively respond to zero-day attacks and multi-vector attacks. The latter shortcoming is the most critical, as evidenced by the constantly increasing number of cyber attacks on the Internet of Things infrastructure. A common limitation for most known approaches is the need for significant computing resources and the significant response time of cyberattack detection systems.

Abstract: The accelerating advancement of quantum computing poses an imminent threat to classical cryptographic schemes, rendering traditional cloud security frameworks increasingly vulnerable. To address this challenge, this study proposes a post-quantum secure cloud architecture that integrates number-theoretic cryptography, artificial intelligence, and blockchain protocols within a scalable deployment model. The framework is built upon lattice-, hash-, and code-based cryptographic primitives whose security is grounded in number-theoretic hardness assumptions, while AI-driven reinforcement learning and deep learning mechanisms provide adaptive resilience through anomaly detection and optimized key management. Blockchain is employed to establish decentralized trust and immutability, supported by post-quantum signature schemes and quantum-safe ledgers, thereby ensuring verifiability across distributed environments. The methodology combines theoretical modeling, simulation environments, and multi-cloud validation to evaluate security, performance, and scalability. Anticipated results include measurable improvements in quantum resistance, reduced latency through AI-optimized cryptographic parameters, and sustained blockchain throughput under post-quantum constraints. Comparative analysis against classical and quantum-ready baselines highlights the superiority of the proposed system in maintaining privacy, efficiency, and interoperability. The findings suggest significant implications for both academia and industry by providing a unified framework capable of safeguarding critical infrastructures in finance, healthcare, and governance. This research contributes to the broader discourse on quantum-safe cybersecurity by demonstrating how interdisciplinary integration—spanning number theory, artificial intelligence, blockchain, and cloud computing—can establish resilient, future-proof digital ecosystems. Keywords Post-quantum cryptography, cloud security, AI-driven cryptography, blockchain protocols, number theory, quantum computing, scalable privacy, decentralized trust, adaptive security, multi-cloud architecture

Edge computing is transforming latency‑sensitive systems such as autonomous vehicles, Industrial IoT, and smart infrastructure. Yet, when managed by centralized Software‑Defined Networking (SDN) controllers, these environments face complex security risks. Existing defenses are largely reactive, acting only after damage occurs. This research introduces a proactive, multi- agent AI security framework in which distributed agents monitor system status, detect anomalies, and recommend real-time policy adjustments. A novel coordination mechanism enables adaptive reconfiguration of SDN policies through programmable APIs. To address resource limitations at the edge, the framework employs federated learning and lightweight, self-optimizing models, delivering efficient and scalable security for resource-constrained environments. Prototyped on open‑source platforms and tested against real‑world attack scenarios, the framework will be evaluated for detection latency, resilience, and response efficiency. The evaluation should show that the framework provides a scalable, context-aware defense that strengthens the resilience of critical infrastructure in heterogeneous domains such as smart cities, healthcare, and energy.

The increasing adoption of cloud computing by federal agencies has introduced significant security challenges, necessitating robust strategies to protect sensitive government data. Traditional perimeter-based security models are no longer sufficient against evolving cyber threats, leading to the need for Zero Trust Architecture (ZTA), AI-driven threat intelligence, and compliance with Cybersecurity and Infrastructure Security Agency (CISA) frameworks. This paper explores how artificial intelligence (AI) enhances federal cloud security by enabling adaptive access controls, automated anomaly detection, and real-time threat response. Zero Trust Architecture (ZTA) eliminates implicit trust in network environments by enforcing continuous verification of users, devices, and workloads. AI augments ZTA by leveraging machine learning (ML) algorithms to detect insider threats, automate authentication, and enforce least-privilege access. Additionally, AI-powered threat intelligence systems improve incident detection and response by analyzing vast data streams to identify attack patterns, phishing attempts, and ransomware indicators in real time. Ensuring compliance with CISA’s cloud security directives is essential for safeguarding federal systems against cyber threats. AI-driven compliance automation tools facilitate real-time monitoring of cloud configurations, detect policy violations, and support continuous diagnostics and mitigation (CDM) strategies. By integrating AI with ZTA and threat intelligence, federal agencies can proactively address cloud security risks, reduce attack surfaces, and strengthen their cyber resilience. This study highlights the transformative role of AI in enhancing federal cloud security, emphasizing the need for intelligent automation, predictive analytics, and regulatory alignment to secure critical infrastructures. Future research should focus on refining AI models for adaptive security orchestration, deception techniques, and proactive threat hunting in federal cloud environments