2022· International Journal of Modern Innovations and Emerging Trends· 0 citations
TL;DR
An in-depth analysis of AI-powered threat detection when it is applied to guarantee network security, its principles, techniques, methodology, and the performance results shows that AI threatened detection systems can greatly increase the accuracy, a decrease in false positives and an increase in the response time in comparison to the usual methods.
Abstract
The expansion in the domains of digital communication, cloud computing, Internet of Things (IoT), and 5G technologies has greatly increased the attack area of the contemporary network infrastructure. The conventional network security measures, which rely mostly on fixed rules and signature-based responses, are becoming incapable of responding to more advanced, changing and zero-day cyber-attacks. Artificial Intelligence (AI) has become a disruptive technology that can be used to improve network security through enhanced and real-time and adaptive threat issues. This paper consists of an in-depth analysis of AI-powered threat detection when it is applied to guarantee network security, its principles, techniques, methodology, and the performance results. The paper is started with the discussion of the limitations of traditional intrusion detection and prevental systems and the necessity of intelligent automation in security problems. It has been thoroughly analyzed with the literature review of the modern progress in the fields of machine learning, deep learning, and hybrid AI applications to network threat detection. The suggested methodology is an AI-based design that includes the process of data gathering, feature engineering, model training, and classifying the threats. Several types of machine learning algorithms are analyzed with reference to their usefulness in identifying anomalous and malicious network behavior, such as supervised, unsupervised and deep learning models. The experimental analysis shows that AI threatened detection systems can greatly increase the accuracy of detection, a decrease in false positives and an increase in the response time in comparison to the usual methods. This discussion examines the performance metrics, scalability, and deployment issues in the actual environments. Lastly, the paper has come to an end by summarizing the major findings and stating the direction of future research moves, which will focus on the role of explainable AI, federated learning, and adaptive defense mechanisms in the next-generation network security systems.
This review presents a comprehensive analysis of machine learning-based intrusion detection systems, covering a wide range of techniques including supervised learning, unsupervised learning, ensemble learning, and deep learning models, and discusses critical challenges affecting the deployment of ML-based IDS.
Ranobir Hasan, H. Jamal, Kamal Kamal et al.· The Eastasouth Journal of In...· 0 citations
The advent of Internet of Things (IoT) and Cyber-Physical Systems (CPS) has led to the rapid development of highly dynamic and complex communication infrastructures in various domains ranging from healthcare, transportation, industrial automation to intelligent energy systems. Even though intrusion detection and network security is a wellresearched research area, existing intrusion detection systems cannot efficiently overcome shortcomings such as unknown threat detection, false-positive alert detection, network adaptivity and improved accuracy with large-scale real-time heterogeneous traffic data. In order to overcome these challenges, this paper proposes an AI-enabled threat detection framework using hybrid deep learning techniques for intelligent cyber threat analysis and intrusion detection. First, network traffic data is pre-processed, Min-Max-normalized, and enhanced by feature selection along with the Principal Component Analysis (PCA)-based dimension reduction to minimise the redundancy and to improve the quality of the dataset. Second, the optimized feature set is leveraged for AIenabled detection of anomalies using Autoencoder, spatial traffic patterns detection using Convolutional Neural Network (CNN), and the temporal dependencies of virtual attacks in traffic data using an LSTM-Recurrent Neural Network (LSTM-RNN). Finally, a hybrid Deep Neural Network (DNN) and Decision Tree classifier on the output of the hybrid model, classifies the normal and malicious network traffic with a reduced false-positive rate. Experimental results of the proposed framework on network intrusion datasets confirmed the efficiency of the proposed framework significantly outperforming the existing standalone deep learning approaches in terms of accuracy, precision, recall, F1-score, scalability, and real-time cyber threat detection.
Ponugoti Kalpana, Pati Ankitha· 2026 5th International Confe...· 0 citations
In the era of contemporary data traffic routing, the concept of Intrusion Detection Systems (IDS) is substantially utilized. However, the efficacy of IDS is often decreased because of the reality that high-concentration traffic postfixes, sophisticated cyber criminals, and more and more stringent demands are tending to decrease in resource-limited environments. The paper presents the enhanced intrusion detection system based on deep learning architecture, which can be flexible, adaptive and as well maintain the high detection capability with confidence under changing or to-be changed network settings. The objectives of this and aforementioned also address the issue of avoiding strong overtting behavior by models during the transfer learning and even rich feature representation through the first-stage operation: moving to address and ideally preventing attacks rather than supporting other attacks. The work is tailored to the deployment of the light-weight and adaptive IDS design which is supposed to be large enough to work in real time on low-powered devices such as IoTs and edge devices that are nondominated in energy and computationally less demanding. Real-time adaptability of the model will be examined through operational deployment simulations. It is also expected that such simulations would take into account latency, throughput, and energy consumption of the IDS model. On the one hand, In a stage nested within the very last period of this research, the IDS model has been merged with Explainable AI technologies; now LIME and SHAP are also preserved to improve the interpretability of the model decisions and the level of decision-making. What kind of feature attributions are made with the intrusion data? How is Interpretability of the model evaluated in terms of fidelity, comprehensibility, and expert belief? Therefore, all the above-mentioned events will be a perfect example of how the technologically ingrained tasks, particularly in the technical discipline of security studies, can be wrapped into the very cognitive resource of human beings.
Krishna Kumar Tiwari· 2026 International Conferenc...· 0 citations
The rapid expansion and spread of networked systems and digital services has tremendously expanded the complexity and frequency of cyberattacks, and conventional security tools are no longer relevant to contemporary cyber threats. Intrusion Detection Systems (IDS) are very important in detection of malicious activities, but the traditional signature based and rule-based IDS are limited in that they have high false-positive, cannot be able to detect the attacks of the zeroday, and fail to be adapted to changing patterns of threats. The recent developments in machine learning (ML) have brought intelligent and adaptive methods that can learn the complicated patterns based on large volumes of network traffic data. This paper provides an in-depth analysis of effective machine learning methods to intrusion detection system in cybersecurity. The paper compares the efficacy of supervised, unsupervised and ensemble-based ML algorithms that conduct intrusion detection with enhanced accuracy, lowered computation load, and improved scalability. It focuses on the feature selection, dimensionality reduction, and model optimization to enhance the detecting performance and retain the capability of running it in real-time. In the results, the hybrid and ensemble models of machine learning prove to be much more efficient than the conventional IDS methods and provide a strong protection against the current cyber threats. This research contributes toward developing intelligent, adaptive, and efficient IDS frameworks suitable for contemporary and future cybersecurity infrastructures.
K. Ashwini, M. Supriya· 2026 5th International Confe...· 0 citations
Critical vulnerabilities have been made public by the fast expansion of Internet of Things (IoT) devices, making these networks easy target for cyber-attacks. While security solutions based on Machine Learning (ML) have shown potential, they often encounter issues including slow detection times, scaling issues, and a lack of generalisability when it comes to diverse IoT devices. To work with these issues, this paper introduces an innovative ML-based security paradigm. The proposed framework improves the attack detection accuracy by combining adaptive feature extraction techniques with a context-attentive hybrid mechanism. The new paradigm maximizes detection accuracy and computational efficiency. This is achieved through real-time dynamic adjustment of feature selection against network conditions, rather than traditional hybrid approaches. Furthermore, a lightweight and scalable detection method fit for execution on low-resource IoT devices is offered. It is apt for several IoT environments. The proposed framework beats several current models by 15% in accuracy, 25% in the reduction of false positive rates, and 30% in detection times, according to experimental tests carried out on numerous IoT datasets.
P. P. Bairagi, Ashish Bagwari, Sailen Dutta Kalita et al.· international journal of eng...· 0 citations
Cloud is the essential component for modern computer systems, offering businesses flexible scalability and on-demand resources. However, as attackers use more complex techniques to compromise cloud networks, this technological advancement has ushered in a new era of cybersecurity challenges. Wide-ranging effects, such as data loss, financial penalties, reputational harm, and legal responsibilities, can result from such breaches. In response to these challenges, a strong security framework is essential to effectively protect cloud infrastructure. Recently, several artificial intelligence (AI) techniques have been developed for cyber threat detection. Hence, to get deeper insight into this, the survey aims to analyse the role of cyber threat detection techniques and provide an overview of their applications. To achieve this, around 28 research papers from the years 2023-2026 are reviewed based on their methods, algorithms, datasets, performance metrics, and achievements. Furthermore, this work reviews different types of threats affecting the availability, confidentiality, and integrity of cloud services and resources, and examines the applications, including intrusion detection in cloud and several types of cyber threat detection systems. The core insights formulated in this review provide a comparison of analytics as well as future directions.
Pradnya Patil, J. Bakal· 2026 7th International Confe...· 0 citations