Zero Trust Architecture (ZTA) represents a paradigm shift in cloud security by challenging the outdated model of implicitly trusting internal networks. Instead of assuming trust based on network location, ZTA treats every access request—whether from inside or outside the network—as potentially malicious. This approach is crucial in cloud environments, where resources are accessed from diverse locations and devices. Implementing ZTA involves rigorous identity verification, robust multi-factor authentication (MFA), and the principle of least privilege, which restricts access to only what is necessary for users and devices. For example, deploying micro-segmentation in cloud environments can reduce the attack surface by up to 80%, effectively isolating workloads and limiting lateral movement during breaches. Advanced threat detection systems, often powered by artificial intelligence and machine learning, are employed to enhance anomaly detection and automate responses to security incidents.
29 August 2025 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
The increasing demand for high-speed wireless connectivity in indoor environments has driven the development of hybrid wireless (Wi-Fi) and light fidelity (LiFi) networks. These systems combine the ubiquitous coverage of Wi-Fi with the high data rates of LiFi, providing an effective solution for dynamic indoor applications such as smart homes, offices, and industrial automation. As a critical component of edge intelligence, hybrid networks enable real-time data processing at the network edge, addressing the connectivity demands of indoor IoT systems. However, deploying these networks in dynamic indoor settings introduces challenges, including managing downlink transmission power, resource allocation, energy consumption, and access point selection amidst varying user mobility and interference. This study proposes a machine learning framework for enhancing edge intelligence, leveraging deep reinforcement learning with a proximal policy optimization algorithm (DRL-PPO) to optimize hybrid Wi-Fi/LiFi network performance in indoor environments. The proposed framework improves channel allocation and load balancing at the edge, ensuring energy efficiency while achieving high data throughput. We also introduce a comprehensive system model to manage dynamic traffic in indoor scenarios and develop resource allocation algorithms for efficient bandwidth distribution. Extensive simulations show that our approach, DRL-PPO, achieves up to an average of 15% higher throughput and 20% lower transmission power compared to baseline methods, demonstrating its potential for real-world deployment in indoor IoT scenarios.
29 October 2025 in Energy Exploration & Exploitation
The complexity of power distribution networks is rising, with smart technologies needed for efficient cybersecurity maintenance and risk management. Securing the scalability of predictive models across different grid configurations, managing massive amounts of sensor data, and integrating diverse data sources are all problems with existing approaches. Therefore, this study presents an artificial intelligence-based dynamic grid optimization analysis (AI-DGOA) method to address the above-discussed potential issues. By dynamically analyzing real-time data, AI-DGOA optimizes grid performance, allowing for proactive decision-making and lowering the risk of power supply disruptions. We design fault detection and classification algorithms based on machine learning ensemble models. The proposed algorithms improve predictive maintenance, reducing maintenance expenses and downtime by detecting impending equipment failures and grid inefficiencies. In addition, AI-DGOA ensures operational resilience and data security by incorporating real-time cybersecurity risk assessment to protect power distribution networks from changing cyber threats. The simulation analysis and results show that AI-DGOA effectively predicts grid disappointments, optimizes load distribution, and predicts cybersecurity vulnerabilities. This study reduces cyber risks, schedules maintenance more efficiently, and increases grid dependability. This study presents the role of Artificial Intelligence (AI) in revolutionizing power distribution networks through better cybersecurity risk management and predictive maintenance, leading to safer and more efficient power grids. Moreover, the extensive analysis shows that the proposed method outperforms other baseline methods, where secured power distribution is a key objective in the networks.
This book chapter looks at the convergence of cybersecurity and cloud computing, emphasizing the importance of securing data and systems in the cloud. It discusses the shared responsibility model for cloud service providers and customers, emphasizing the importance of collaboration in order to ensure comprehensive security. The chapter identifies and addresses various issues in cloud-based system security, such as data loss, insecure APIs, insider threats, and compliance challenges. It also discusses the revolutionary opportunities that result from convergence, such as improved security posture, cloud-native security solutions, advanced threat detection, and improved incident response. The convergence's limitations and considerations, such as the shared responsibility model, data privacy, and reliance on internet connectivity, are also discussed.
At present the world has moved to cyber space with latest technologies and different network systems. To protect the systems, files and data in a network cyber security play a key role in the digital world. The cyber security is most essential technology for protecting organization, financial and industry data securely from attackers to maintain sensitive information. Due to everything is digitalized in the present days there is a lot of data is transferred in terms of documents or files in the cloud. Cloud computing is a new platform to provide different services like infrastructure, software to the different end users based on their demand. So maintaining the data securely in the cloud there is a necessity of finding the different threats in a network and systems for reducing the risks and take effective decisions. In this chapter we discussed about different threats and risks related to cyber security and how to maintain the identity in the cloud based systems.
As technology evolves, the cyber wars are increasing very fast. One of the most dangerous threats is ransomware. As the ransomware threats keep increasing, it demands more advanced equipment. Inception Net and dense Net will help in detecting the ransomware. This chapter gives a new approach that combines the strengths and capabilities of both pre-trained models (Inception Net and Dense Net). Inception Net was used here because it shows its effectiveness in image analysis. Mainly, it is used in visual data that belongs to potential ransomware attacks as a feature extractor. Whereas the other model is dense Net. It has a feature that can analyze sequenced and structured data. This innovative approach increases the capacity for detecting ransomware threats around different types of data sets. Mainly, it will encourage a strong defense against dangerous cyber threats.