ENHANCING BLOCKCHAIN SECURITY WITH MACHINE LEARNING: A COMPREHENSIVE STUDY OF ALGORITHMS AND APPLICATIONS

Blockchain technology offers secure, decentralized systems but faces increasing threats like double-spending and Sybil attacks. This study evaluates machine learning algorithms, including Random Forest, K-Means, and Deep Q-Networks, to enhance blockchain security. Experimental results show Deep Q-Networks and XGBoost outperform other models, achieving 97.8% accuracy and 0.99 AUC-ROC, demonstrating their effectiveness in real-time threat detection. This research highlights the potential of machine learning to safeguard blockchain systems and suggests future directions, such as federated learning for collaborative security and explainable AI for improved transparency.

Phishing attacks are a major cybersecurity threat, exploiting human vulnerabilities by manipulating trust to access sensitive information. As phishing tactics evolve, the demand for advanced anti-phishing technologies has surged. This paper examines key measures such as email filters, SSL/TLS certificates, DNS-based authentication, multi-factor authentication, and URL filtering to protect against phishing. Advanced methods like machine learning, AI-driven analysis, and real-time threat detection have improved phishing prevention. It also discusses browser-based, cloud-based, and email security tools for mitigating risks. The paper highlights challenges such as evolving tactics, email filtering limitations, and user negligence, emphasizing the need for ongoing innovation in strategies. Future trends like AI, biometrics, and deep learning for threat intelligence are explored, showing potential to enhance phishing defense. A holistic approach integrating technology, protocols, and user awareness is advocated to combat phishing effectively at both individual and organizational levels.

The Internet of Things (IoT) has transformed various sectors by enabling connectivity and automation through smart devices. However, the expansion of IoT networks has introduced new security challenges, particularly concerning the detection and prevention of cyber threats. This study explores the application of machine learning (ML) models for enhancing network security in IoT-enabled smart systems. The primary objective was to evaluate the performance of different ML algorithms, including Convolutional Neural Networks (CNN), Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), K-Means, and Autoencoder, in detecting and mitigating security threats in IoT environments. The study also aimed to identify the most effective model in terms of accuracy, precision, recall, and F1-score. The research methodology involved training and testing these models on publicly available IoT security datasets, followed by performance evaluation based on the key metrics. Statistical analysis, including One-Way ANOVA and post-hoc testing, was used to assess the significance of the performance differences across the models. The results revealed that CNN outperformed all other models, achieving the highest accuracy (96.7%), precision (95.8%), recall (97.2%), and F1-score (96.5%). Random Forest also demonstrated strong performance with an accuracy of 95.6% and a balanced evaluation across all metrics. In contrast, traditional models like SVM and DT showed comparatively lower performance, while Autoencoder struggled with classification tasks, particularly in real-time threat detection. Statistical analysis confirmed the significant differences in model performance. In conclusion, the study demonstrates the effectiveness of deep learning and ensemble models, particularly CNN and Random Forest, in enhancing IoT network security. The research highlights the importance of selecting the appropriate ML model based on the specific requirements of the IoT environment and computational constraints, and suggests that hybrid models and model optimization strategies may offer promising solutions for resource-constrained IoT systems.

In the evolving landscape of modern IT infrastructure, organizations are increasingly adopting hybrid environments that combine on-premises data centers with cloud solutions to meet scalability, flexibility, and operational efficiency needs. However, managing the security and performance of such complex environments introduces unique challenges, particularly in areas like network segmentation, vulnerability management, and real-time threat detection. This case study explores the implementation of an AI-powered network infrastructure audit and security framework for a global retail company operating in both on-premises and cloud environments. The company’s data center infrastructure relies on Cisco devices, including Cisco ACI (Application Centric Infrastructure) for network segmentation, Cisco Firepower NGFW for intrusion prevention, and Cisco Umbrella for DNS-level protection. The core of this approach involves leveraging AI-driven tools to automate vulnerability management, threat detection, and response across both on-premises systems and cloud environments (AWS, Azure). The study illustrates how Cisco ACI and AWS Security Hub were used to segment networks and isolate sensitive data, minimizing the attack surface. Furthermore, the integration of Qualys VMDR for automated vulnerability scanning and patch management, combined with Ansible for efficient patch deployment, improved operational efficiency and reduced manual intervention in vulnerability remediation. Cisco Tetration provided enhanced visibility into workload behaviors across both environments, ensuring that unauthorized lateral movements were prevented. The implementation of AI-driven security analytics through Cisco Firepower and Umbrella allowed for rapid identification and mitigation of potential threats. Additionally, the study highlights the importance of automated compliance reporting, with tools like ServiceNow integrated for tracking remediation efforts and generating compliance reports for industry standards such as PCI-DSS and GDPR. By deploying a combination of advanced network segmentation, real-time threat detection, and automated remediation, the company achieved significant improvements in its security posture, operational efficiency, and compliance. This case study serves as a comprehensive example of how AI-powered security tools and Cisco devices can be effectively integrated to address the complexities of managing a hybrid IT infrastructure while ensuring that both on-premises and cloud environments remain secure, efficient, and compliant. The results of this implementation demonstrate the value of combining cutting-edge security technologies with automation to drive proactive risk management and operational excellence

A blockchain-enabled Model integrates blockchain technology with Intrusion Detection Systems to enhance the security of Internet of Things (IoT) networks. It ensures data integrity, decentralization, and tamper-proof logging of intrusion detection. The approach improves trust, transparency, and real-time threat detection in distributed IoT environments. The existing blockchain-based IDS approaches, Blockchain Enabled (BCE-IoT), uniquely integrate blockchain consensus with federated-style local training, lightweight cryptography, and Shapley Additive Explanations (SHAP)-based explainability, ensuring both security and interpretability in IoT environments. The proposed work combines Blockchain technology with explainable artificial intelligence solutions to create a new cybersecurity Model that strengthens intrusion detection within IoT networks. The proposed model enhances transparency in tracking cyberattacks by combining blockchain security storage capabilities with SHAP, an explainable AI. This research utilises machine learning and artificial intelligence to detect threats in real-time, countering Distributed Denial of Service (DDoS), Denial of Service (DoS), scanning, Cross-Site Scripting (XSS), injection, password, and backdoor attacks. BCE-IoT delivers more precise security by combining blockchain’s permanent data features and AI anomaly detectors, thereby reducing security alert mistakes. The performance effectiveness of Blockchain-Enabled IoT surpasses that of the Content Integrity Detection System. It combines Blockchain and Software-Defined Networking to enhance security in network environments, utilising blockchain-based mutual confirmation for software-defined networking to detect and block cyber threats. The evaluation establishes BCE-IoT as an effective IoT network security solution that delivers strong cybersecurity features, is adaptable to modern connected environments, and offers interpretable security solutions. The performance evaluations demonstrate that BCE-IoT provides a robust, flexible, and interpretable cybersecurity solution suitable for modern IoT environments.

Due to cyber threat complexity, perimeter-centric security must be replaced with smarter, more dynamic solutions. Zero Trust Architecture (ZTA), which advocates for "never trust, always verify," is the most widely adopted security model. ZTA benefits from real-time anomaly detection, adaptive access, and predictive threat response with AI. It describes how AI-powered ZTA can thwart advanced cybersecurity assaults in hybrid and multi-cloud systems. It covers identity-based authentication, real-time threat detection, dynamic policy enforcement, and contextual analysis. Businesses can now gain deep insights into network behavior and automate security measures using AI technologies, such as machine learning and behavioral inspection. Real-time simulations and security log data are used in the mixed-method research. AI-augmented ZTA prevents breaches, reduces reaction time, and increases threat visibility in modern networks. AI-enabled Zero Trust policies use tables and graphs to improve detection accuracy and system integrity. The architecture supports scalability, modularity, and integration with cybersecurity frameworks. A novel scalable enterprise network cybersecurity design and an AI-driven Zero Trust paradigm are described in the essay. The study concludes with implications, limits, and future research options. The findings necessitate that organisations implement AI-driven ZTA as a permanent defence against cyber threats.

Machine learning has been attracting significant attention again since the potential of deep learning was recognized. Not only has machine learning been improved, but it has also been integrated with “reinforcement learning,” revealing other potential applications, e.g., deep Q-networks (DQN) and AlphaGO proposed by Google DeepMind. It is against this background that this special issue, “Cutting Edge of Reinforcement Learning and its Hybrid Methods,” focuses on both reinforcement learning and its hybrid methods, including reinforcement learning with deep learning or evolutionary computation, to explore new potentials of reinforcement learning.Of the many contributions received, we finally selected 13 works for publication. The first three propose hybrids of deep learning and reinforcement learning for single agent environments, which include the latest research results in the areas of convolutional neural networks and DQN. The fourth through seventh works are related to the Learning Classifier System, which integrates evolutionary computation and reinforcement learning to develop the rule discovery mechanism. The eighth and ninth works address problems related to goal design or the reward, an issue that is particularly important to the application of reinforcement learning. The last four contributions deal with multiagent environments.These works cover a wide range of studies, from the expansion of techniques incorporating simultaneous learning to applications in multiagent environments. All works are on the cutting edge of reinforcement learning and its hybrid methods. We hope that this special issue constitutes a large contribution to the development of the reinforcement learning field.

In the rapidly advancing field of industrial automation, Programmable Logic Controllers (PLCs) are fundamental to maintaining efficient and reliable control systems. This paper explores the integration of Artificial Intelligence (AI) into PLC systems to enhance industrial control processes. We investigate the application of AI techniques, such as machine learning and deep learning, for predictive maintenance, anomaly detection, and adaptive control, thereby improving system performance and reducing downtime. In parallel, we address the paramount concern of data privacy, presenting advanced encryption methodologies and secure communication protocols to protect sensitive industrial data. Our research highlights the dual benefits of incorporating AI into PLC systems: significantly elevating the intelligence and adaptability of industrial operations while simultaneously ensuring robust data security measures. The study's outcomes reveal the transformative potential of secure and intelligent PLC systems in shaping the future of smart manufacturing, aligning operational efficiency with stringent data privacy standards.Through an analysis of existing frameworks and case studies, we illustrate the effectiveness of these AI strategies in mitigating privacy risks while maintaining data utility for analytical purposes. Additionally, we highlight the advantages of using AI for data privacy, such as enhanced scalability, real-time threat detection, and the ability to adapt to evolving privacy challenges. Furthermore, we address the inherent challenges in balancing data privacy with AI capabilities, such as computational overhead, algorithmic transparency, and ethical considerations. By examining these issues, our study provides valuable insights and proposes future research directions to enhance the privacy-preservation landscape. This paper aims to contribute to the ongoing discourse on AI and data privacy, offering actionable strategies for researchers, practitioners, and policymakers dedicated to protecting sensitive data in an increasingly interconnected world.

Abstract-The increasing use of IoT devices has led to growing cybersecurity threats, making traditional Intrusion Detection Systems (IDS) ineffective against evolving attacks. This project proposes an AI-powered IDS that integrates Machine Learning (ML), Deep Learning (DL), and Blockchain to detect and prevent cyber threats in real time. The system employs CNN, LSTM, and Isolation Forest for anomaly detection, Neuromorphic Computing (SNNs) for fast processing, and Blockchain for secure logging. Additionally, Reinforcement Learning (RL) enables autonomous security adaptation. The proposed system enhances IoT security, real-time threat detection, and self-healing capabilities, making it a robust solution for modern cyber challenges.

The proliferation of Internet of Things (IoT) devices in personal and household environments has led to a significant increase in security vulnerabilities. These devices, due to their limited computational resources, often struggle to support conventional security solutions, making them prime targets for cyberattacks. This paper explores the potential of lightweight machine learning (ML) models to enhance the security of personal IoT devices. By leveraging the power of AI, lightweight models can offer real-time threat detection and anomaly identification without compromising the device's performance or requiring extensive computational resources. The paper investigates various ML techniques that are well-suited for IoT environments, such as decision trees, k-nearest neighbours (KNN), and support vector machines (SVM), focusing on their ability to detect intrusions, unauthorized access, and other malicious activities while maintaining efficiency. Additionally, the study highlights the trade-offs between model complexity, accuracy, and resource consumption, offering practical insights for deploying ML solutions in resource-constrained IoT systems. Key challenges, including data privacy, model generalization, and the adaptability of models to diverse IoT ecosystems, are addressed. Finally, the paper discusses future directions for the integration of more advanced lightweight models, such as federated learning and edge computing, which could further enhance security capabilities while ensuring minimal impact on IoT device performance. Through this review, the paper advocates for the adoption of lightweight ML models as a feasible and scalable solution to securing personal IoT devices in an increasingly connected world.

Abstract: This study investigates a hybrid Quantum-AI framework for real-time cybersecurity threat detection and adaptive defense in high-velocity network environments. The central research problem concerns the increasing mismatch between dynamic cyberattacks and conventional intrusion-detection pipelines that are accurate under benchmark conditions but insufficiently reliable under latency, drift, explainability, and verification constraints. The proposed framework combines classical representation learning, quantum-inspired feature mapping, calibrated risk scoring, and an LR validation framework composed of a reasoning agent, a proof agent, and a verification layer. The framework is designed to improve detection of heterogeneous threats while reducing unsupported explanatory claims and unsafe automated responses. The empirical design uses publicly documented cybersecurity benchmarks and a realistic pooled evaluation structure based on UNSW-NB15, CICIDS2017, and ToN-IoT network telemetry. These datasets provide labelled flows, attack categories, IoT/IIoT telemetry, and widely used cyber-range traffic profiles suitable for evaluating intrusion detection under realistic operational conditions. Mathematical equations are embedded to formalise feature encoding, quantum-kernel similarity, risk calibration, adaptive policy selection, and proof-verification constraints. Results indicate that the Hybrid Quantum-AI + LR validation configuration achieves the strongest benchmark profile, with a macro F1 of 0.969, ROC-AUC of 0.994, and median inference latency of 11.8 ms in the constructed evaluation table. The findings suggest that coupling high-dimensional detection with formal validation can strengthen both technical performance and operational trustworthiness in cyber-physical and enterprise environments. The contribution of the paper is threefold. First, it provides a rigorous architecture for combining quantum-inspired embeddings with temporal AI models for intrusion detection. Second, it specifies an LR validation framework that converts tentative reasoning into machine-checkable obligations, thereby reducing hallucinated explanations and inconsistent defense actions. Third, it demonstrates how real-data benchmark sources and domain-plausible operational metrics can be used to evaluate detection, latency, adaptation, and verification quality in a unified manuscript structure aligned with high-level journal and doctoral research expectations. Keywords: Quantum-AI; intrusion detection; adaptive cybersecurity; real-time threat detection; quantum kernel; formal verification; reasoning agent; proof agent; network telemetry; cyber defense automation.

The rapid digitalization of healthcare systems has led to an unprecedented accumulation of sensitive patient data across various platforms, exposing the industry to growing risks of data breaches, unauthorized access, and integrity compromise. Ensuring the security, privacy, and trustworthiness of healthcare data is paramount to maintaining patient confidentiality and enhancing clinical decision-making. This study proposes a conceptual framework that synergistically integrates Blockchain technology and Artificial Intelligence (AI) to enhance healthcare data security. The framework is designed to address key challenges such as data integrity, access control, real-time threat detection, and secure interoperability across healthcare stakeholders. Blockchain, with its decentralized and immutable ledger capabilities, provides a robust foundation for tamper-proof data storage and transparent audit trails. Smart contracts are employed to automate access controls and ensure compliance with regulatory requirements. AI, on the other hand, plays a critical role in intelligent threat detection and anomaly monitoring. By leveraging machine learning algorithms, the framework can identify suspicious patterns, detect insider threats, and predict potential breaches in real time. The proposed architecture comprises four core components: Secure data ingestion, blockchain-based data storage, AI-powered analytics, and a privacy-preserving access management layer. The framework also incorporates role-based authentication and homomorphic encryption techniques to enhance data privacy while supporting authorized data sharing. Case scenarios such as electronic health record (EHR) exchange and remote patient monitoring are used to demonstrate the practicality and scalability of the model. This integrated approach not only ensures the confidentiality, integrity, and availability of healthcare data but also fosters trust among patients, providers, and regulatory bodies. The framework aligns with global healthcare data standards and complies with regulations such as HIPAA and GDPR. Future directions include the deployment of federated learning models to further decentralize AI training while maintaining data privacy across institutions.

Public safety increasingly demands advanced surveillance systems capable of automatic and real-time threat detection. This study addresses this need by proposing a multimodal surveillance system that integrates face recognition, hand gesture detection, and body pose estimation to enhance threat detection accuracy. The system employs the MediaPipe algorithm to analyze video inputs in real time and promptly issue alerts when threats are identified. These alerts are forwarded to a mobile application linked to the camera network, allowing security personnel to respond immediately. Experimental evaluation demonstrates the system’s capability to improve situational awareness and reduce response latency. This approach offers a practical solution for enhancing public safety through the application of computer vision and real-time notifications.

The speed of the development of cloud computing and mobile networks has brought significant security risks that require innovative solutions to secure volatile and decentralized environments. The conventional models of perimeter-based security do not fit this scenario because they do not support the dynamics and multi-faceted nature of new threats to the network. This paper outlines a standalone security system coupled with the Zero Trust architecture and dynamic threat detection system to allow a greater level of security in cloud and mobile networks. The system suggested would guarantee constant verification of users, devices, and applications, with the use of AI-driven threat detection, whereby breaches to security are detected and addressed automatically. The proposed framework is experimentally evaluated and found to be very effective as compared to the traditional security models. The autonomous framework has a detection accuracy of 98.4% as opposed to the traditional models with a detection accuracy of 85.2%. In addition, the system was shown to have a much shorter response time (45 ms vs. 150 ms) and false positive rate (4.1% vs. 12.3%), as well as scalability because it could support up to 5000 users (compared to the 500 users that the traditional systems could support). This is indicative of the system in capturing large-scale dynamic networks. The inclusion of the Zero Trust principles further improves the security of the network since no user or device will be trusted by default, no matter where they are located. The autonomy of the system allows it to constantly adapt to new threats to enhance its capability to respond to changes in attack vectors. The paper identifies that the proposed approach is a scalable real-time solution to the current security dilemma facing cloud and mobile networks, which offers firm protection against internal and external threats. Further optimization of the system to deploy even bigger ranges will be considered in future work, and more rational methods of AI will be integrated.

The development of autonomous wearable perception devices with real-time environmental awareness has been sped up by the convergence of robotics, embedded systems, and artificial intelligence (AI). However, the majority of current assistive and surveillance systems are still limited by their static deployment, reliance on networks, and subpar performance in low-visibility scenarios. The theoretical underpinnings and literature review of a wearable artificial intelligence system for dual-spectrum analysis and real-time threat detection are presented in this research. Mounted on a small robotic arm platform, the device incorporates a dual-camera vision module that combines an RGB sensor for daylight and an infrared night-vision sensor for darkness. Optimized lightweight deep-learning models converted to TensorFlow Lite are used to handle the visual data fully on edge devices like the Google Coral Dev Board or Raspberry Pi 4. Users without cloud access can receive instant spatial alerts thanks to the design's ability to detect objects on-device and provide multimodal feedback (tactile and audio). Defense surveillance for autonomous threat identification and assistive navigation for visually impaired people are the two applications that the framework is intended for. This paper highlights research gaps in wearable edge-AI systems for adaptive multimodal perception by concentrating on the theoretical underpinnings and literature synthesis supporting the development.