Aug 2026· International journal of computer information systems and industrial management applications· Vol 18, pp. 550-558· 0 citations
TL;DR
This review paper critically examines the integration of Artificial Intelligence (AI) and Machine Learning (ML) techniques to enhance information security within Cloud-IoT networks, focusing on hybrid Deep Learning models (CNN-LSTM), predictive analytics, and automated threat response mechanisms.
Abstract
The convergence of Cloud Computing and the Internet of Things (IoT) has created a hyper-connected ecosystem that drives modern industry but simultaneously expands the cyber-attack surface. Traditional security mechanisms, such as static firewalls and signature-based intrusion detection, are increasingly insufficient against sophisticated, polymorphic threats like Distributed Denial of Service (DDoS) and zero-day exploits. This review paper critically examines the integration of Artificial Intelligence (AI) and Machine Learning (ML) techniques to enhance information security within Cloud-IoT networks. We analyze the current state of AI-driven frameworks, focusing on hybrid Deep Learning models (CNN-LSTM), predictive analytics, and automated threat response mechanisms. A systematic literature survey of recent advancements identifies key trends, including the shift towards decentralized learning and real-time adaptive defense. Furthermore, we critically analyze the limitations of existing approaches, such as computational overhead and data privacy concerns. Finally, this paper identifies significant research gaps and provides strategic recommendations for developing robust, scalable, and intelligent security architectures for next-generation environments.
The rapid expansion of the Internet of Things (IoT) has enabled pervasive connectivity and intelligent automation across multiple sectors, while simultaneously exposing networks to significant security vulnerabilities. Among these vulnerabilities, Distributed Denial-of-Service (DDoS) attacks remain one of the most critical threats due to their scalability, persistence, and effectiveness against resource‑constrained IoT devices. This paper presents a comprehensive literature review of DDoS detection and mitigation techniques in IoT environments, emphasizing traditional methods, machine learning, deep learning, and ensemble-based approaches. The review is structured into four major sections: the IoT and DDoS threat landscape; traditional and machine learning-based detection techniques; deep learning and ensemble approaches; and open challenges with future research directions. By synthesizing existing studies, this paper provides a coherent academic foundation for the design of adaptive, scalable, and intelligent IoT security frameworks.
Solanke Oluwole, Alao Olujimi D, Akande Oyebola· International Journal Of Eng...· 0 citations
The proliferation of Internet of Things (IoT) devices across healthcare, smart cities, industrial automation, transportation, and agriculture has ushered in an era of unprecedented connectivity and data generation. Despite these advances, conventional IoT architectures remain fundamentally constrained by limited battery capacity, restricted computational resources, and growing exposure to sophisticated cyber-threats. Artificial Intelligence of Things (AIoT)—the convergence of artificial intelligence (AI) with IoT infrastructure—has emerged as a transformative paradigm capable of addressing these systemic limitations. This paper presents a thorough and structured review of AIoT with a dual emphasis on energy optimization and node-level security. We systematically examine the AIoT layered architecture, state-of-the-art machine learning and deep learning approaches for energy management, AI-driven intrusion detection systems, blockchain-based trust frameworks, lightweight cryptographic primitives, and federated learning mechanisms. Furthermore, the interplay between energy efficiency and security overhead is critically analyzed. Key open challenges, including scalability, real-time attack detection, privacy preservation, and standardization gaps, are identified, and a forward-looking research agenda is proposed. This review aims to serve as a consolidated reference for researchers and practitioners seeking to develop secure, energy-aware, and intelligent AIoT ecosystems.
Rishi Kumar Sharma, Raghu Nandan Singh Hada, Md. Shahbaz Khan· International journal of res...· 0 citations
The rapid growth of Internet of Things (IoT) devices has significantly improved connectivity across smart environments. However, the resource-constrained nature of IoT devices and their limited built-in security mechanisms make them highly vulnerable to evolving cyberattacks. Traditional intrusion detection systems relying on signature-based or static rule sets are often ineffective against previously unseen attacks. This study proposes a hybrid machine learning-based intrusion detection and prevention framework for securing IoT networks. The framework integrates Isolation Forest, Autoencoder, Extreme Gradient Boosting, and Bidirectional Long Short-Term Memory models within a stacked ensemble architecture to improve attack detection while reducing false-positive predictions. The ensemble outputs are combined using a Logistic Regression meta-classifier to generate the final threat score. Experimental evaluation using the UNSW-NB15 dataset demonstrates that Extreme Gradient Boosting achieved the highest individual Receiver Operating Characteristic-Area Under the Curve score of 0.91, while the proposed framework further enhances detection robustness through ensemble learning and automated prevention. A Flask-based monitoring dashboard provides real-time visualization of detection results, blocked IP addresses, alerts, and system performance.
Ruthwik Palem, Likhith Reddy Peketi, Vanathi M et al.· Cureus Journal of Computer S...· 0 citations
The exponentially increasing number of IoT devices and their corresponding cloud infrastructures increases the attack surface․ Classic rule-based schemes and cryptographic solutions are not well adapted to dynamic‚ heterogeneous‚ distributed‚ and resource-constrained IoT-cloud infrastructures․ Artificial intelligence (AI) based techniques such as machine learning (ML)‚ deep learning (DL) and federated learning (FL)‚ considered as a new model for intrusion detection systems (IDS) to assess the threats in real time and respond to the threats effectively in the dynamic environment․ This paper thoroughly reviews the state-of-the-art AI-based IDS in a layer-wise manner which consists of IoT and cloud stacks․ It categorizes popular cyber-attacks associated with each layer (perception‚ network‚ transport‚ processing and application) and correlate the attacks to machine learning classifiers (SVM‚ KNN‚ Random Forest‚ CNN‚ RNN/LSTM‚ Autoencoder) at shallow and deep learning levels․ The research incorporates federated IDS‚ graph neural networks‚ transformer architecture and explainable artificial intelligence as models of machine learning and further discusses prominent research issues (data scarcity‚ adversarial robustness‚ latency‚ transferability) and the future direction of next-generation IoT-cloud security․
A. Anitha, A. R, Arpita Nath Boruah et al.· International journal of com...· 0 citations
Industrial internet of things (I-IoT) is the core of industry 4.0 that refers to the fourth industrial revolution, characterized by the integration of digital technologies into various aspects of industrial processes. It is a paradigm shift that combines traditional manufacturing with the latest smart technology. Ensuring the security of these devices is crucial, acting as a key element for the smooth flow of operations within the organization. Moreover, building a strong cybersecurity framework not only protects against potential threats but also nurtures a climate of trust and dependability in industrial processes. However, traditional security methods struggle due to the limited storage and computing capacity of I-IoT devices. On the other hand, machine learning techniques, specifically employing intrusion detection S, offer improved efficacy in identifying both unknown and zero-day attacks. To address this challenge, we integrate an eXtreme gradient boosting (XGBoost) model, known for its learning capabilities, enabling efficient detection of diverse attacks without encountering overfitting problems. We evaluated the reliability, efficiency, and flexibility of our model by utilizing two diverse datasets, incorporating network, IoT, and I-IoT traffic. The first dataset is considered medium in size, while the second is characterized as large and complex. Our XGBoost model showcased remarkable efficiency, outperforming previous studies across key evaluation metrics accuracy, F1-score, recall, and precision. It displayed exceptional proficiency in identifying various attack types within both medium and complex datasets, yielding consistently high-performance outcomes. Notably, it achieved perfect scores of 100% across all evaluation metrics for X-IIoTID and an impressive 99.88% for Edge-IIoTSet.