Oct 2026· International Conference on Innovative Mechanisms for Industry Applications· pp. 560-565· 0 citations· 15 references
TL;DR
An AI-Driven Threat Detection and Autonomous Response Framework, which uses machine learning algorithms to detect, classify, and respond to modern cyber attacks through network traffic analysis, and it features intelligent autonomous responses to cyber attacks.
Abstract
Modern cyber infrastructure is continuously facing highly complex cyber attacks that have evolved beyond the capacity of signature-based cyber-security systems to effectively protect networks. This has led to the need for intelligent and autonomous cyber-security solutions that are capable of detecting and neutralizing cyber threats in real time. This paper proposes an AI-Driven Threat Detection and Autonomous Response Framework, which uses machine learning algorithms to detect, classify, and respond to modern cyber attacks through network traffic analysis. In particular, the framework makes use of the UNSW-NB15 benchmark dataset to detect and classify various forms of modern cyber attacks, which include but are not limited to exploits, fuzzers, backdoors, reconnaissance, shellcode, worms, denial-of-service attacks, and other general attacks on the computer network infrastructure. The framework features intelligent autonomous responses to cyber attacks, and it includes simulated cyber operations, such as attack logging, attack alerting, malicious activity quarantine, and network traffic blocking. As demonstrated by the results obtained from implementation of the proposed framework, the proposed cyber threat detection system is robust, scalable, and operationally feasible for intrusion detection.
As attacks evolve in both frequency and sophistication, traditional security systems have proven ineffective in handling the threats because they are very heavily signature and manual dependent. In today's network environment, intelligent defense systems that can detect threats that are changing and reacting quickly in...
Aswini M. P., Soundhar P, Gobinathan M et al.· 2026 International Conferenc...· 0 citations
The proposed suggested system proves that ensemble learning based on the Random Forest along with optimized feature selection can increase the reliability of cyber attack detection and computational efficiency to a considerable extent.
Nirmal Kumar Jingar, Cheema Priyanka, A. Thaseen· 0 citations
An AI-Based Smart Honeypot System for Cyberattack Intelligence that combines machine learning, behavioral analysis, and deception techniques for detecting malicious activities in real time and shows improved detection accuracy with reduced false positives.
Jakkamreddy Damodhar Reddy, A. M, Gottipati Pavan Kumar· International Journal of Tec...· 0 citations
DefenX-AI is introduced, an adaptive cybersecurity framework that leverages AI-driven threat intelligence and multi-agent learning to autonomously detect, predict, and mitigate evolving attacks in real time.
J. Glory, P. Ezhumalai, V. Sharmila et al.· 2026 IEEE International Conf...· 0 citations
It is concluded that an effective AI-powered IDS requires reliable data, careful validation, privacy protection, analyst oversight, and continuous monitoring.
P. T. D. Sandhya Pawar, H. B. J. G. R. Sarode· International Journal of Adv...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.