Jul 2026· International Journal of Advanced Research· 0 citations
TL;DR
An attack taxonomy of the proposed system is presented, mimicking real-world attacks such as Denial of Service, Man-in-the-Middle, and insider attacks, to show how the system can detect, counter, and prevent risks successfully and efficiently in the overall network.
Abstract
With the rising complexity and frequency of cyber threats, enterprises require intelligent, proactive systems that can detect and mitigate risks in real time to safeguard critical infrastructure and data. This paper presents an attack taxonomy of the proposed system, mimicking real-world attacks such as Denial of Service (DoS), Man-in-the-Middle (MitM) scenarios, and insider attacks. Some of the principal components in the system architecture include the Intrusion Detection System (IDS), the decision-making system, and the response regimen. The outputs measured in throughput, latency, packet loss, detection accuracy, and resource utilization are used to formulate simulation KPIs. Outcomes show how the system can detect, counter, and prevent risks successfully and efficiently in the overall network. Some of the evident findings involve using AI in making decisions that would eliminate false positives and increase the detection percentage. Hence, the study recommends using easily scalable artificial intelligence models to support cybersecurity frameworks and expanding simulations in the real environment.
Cyberattacks are becoming more frequent and sophisticated in today’s digital world, rendering conventional security measures inadequate. In order to increase the accuracy of cyber threat detection, this study investigates the application of deeplearning methods to increase the accuracy of cyber threat detection. A cybersecurity dataset was used to test four classification models: Artificial Neural Networks (ANN), Random Forest, XGBoost, and Logistic Regression. The models were evaluated using the key 95.32. The performance of Artificial Neural Networks, Random Forest, XGBoost, and Logistic Regression was examined. These findings imply that learning-based and ensemble models are better at spotting intricate and changing attack patterns. In general, the study highlights the significance of clever, data-driven methods for creating cybersecurity defence systems that are quicker, more dependable, and more resilient.
D. Sharma, Inderdeep Kaur, Krishika Gupta et al.· International Conference on...· 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 results show that XAI can improve the transparency, trustworthiness and effectiveness of AI-based cybersecurity systems, in addition to highlighting a range of privacy, adversarial robustness, scalability and evaluation challenges that warrant further research to ensure reliable deployment in the real world.
Raman Kumar· International Journal of Adv...· 0 citations
An Advanced Machine Learning Model for Anticipating and Preventing Cyber Attacks Using Random Forest is presented, which effectively detects cyber threats with high accuracy and reliability, thereby improving threat anticipation and reducing security risks.
T Pushpalatha and RP Rajeshwari· International Journal of Adv...· 0 citations
The rapid increase in the number of cyberattacks in the digital age has reduced the effectiveness of conventional cybersecurity systems. Traditional methods of cybersecurity face considerable difficulty when detecting new, sophisticated attacks and advanced exploitation techniques swiftly. This research addresses critical cybersecurity concerns by developing an AI-driven Intrusion Detection System (IDS), which employs Random Forest (RF) algorithms to detect cyberattacks efficiently. The evaluation of the model was conducted using three publicly available datasets: CICIDS2017 (692,703 records), NSL-KDD (148,517 records), and UNSW-NB15 (257,673 records) with various attack backgrounds and network configurations. A set of evaluation metrics, including accuracy, precision, recall, and F1-score, was employed to assess the performance of the cyberattack detection prototype. Across the three datasets, the model attained an average accuracy of 99.85%, precision of 99.83%, recall of 99.91%, and an F1-score of 99.87%, while maintaining low error rates, with an average false positive rate of 0.25% and a false negative rate of 0.10%. The results indicate that Random Forest is an effective solution for cyberattack detection in data-driven environments. The model was developed with lightweight and easy-to-deploy criteria, but the evaluation reported in this study was done under benchmark test conditions. This work improves the effectiveness of machine learning-based intrusion detection systems and serves as a stepping stone for future research on operational and real-time deployment of machine learning-based intrusion detection systems.
Phathutshedzo Cyprin Ramuhovhi, Naume Sonhera, T. Zuva· Latin American Journal of Co...· 0 citations
Background: India faced a surge of cyber threats, from their frequency to sophistication, as the growth of Digital Technologies, Cloud Computing, Internet of Things (IoT), Artificial Intelligence (AI), and the rise of online financial services. In this regard, machine learning (ML) is a potential solution that offers intelligence, adaptability, and real-time detection and prevention of cyber threats. While the studies on ML applications in the field of cybersecurity have been conducted, a thorough synthesis study on the available evidence on cybersecurity in the Indian context has yet to be carried out.Objective: This systematic review will focus on evaluating the literature related to machine learning techniques for real-time cyber threat detection and prevention in India.Methods: This study used a systematic review design and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines were followed. A thorough literature search was performed in all major electronic databases such as IEEE Xplore, Scopus, Web of Science, ScienceDirect, SpringerLink, ACM Digital Library and Google Scholar. The articles were included if they were published in English and reviewed by peers from 2020-2026.Conclusion: Machine learning has proven to be a transformative technology for enhancing cybersecurity, with its ability to detect threats intelligently, adaptively, and automatically. Despite the progress made, there is still a need for more research and development to build easily explainable, scalable, and context-specific machine learning models that can adapt to India's growing cybersecurity challenges. The insights from this review offer tangible support for researchers, practitioners, and policymakers in their quest for enhanced AI-driven cybersecurity solutions and a more secure digital landscape.
Kartikeya Tiwari· International journal of com...· 0 citations