Adaptive AI-Driven Intrusion Detection Systems: Enhancing Threat Response in Real Time

• Author(s): Nageshwar Masakapalli
• Paper ID: 1707995
• Page: 487-497
• Published Date: 31-12-2023
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 7 Issue 6 December-2023

Abstract

Advanced cyber attack development in the present age creates difficulties for IDS in identifying new adaptive attack techniques in real time. The text describes how Adaptive AI-driven Intrusion Detection Systems (AI-IDS) utilize artificial intelligence alongside machine learning to develop AI-based intrusion detection through their development process. AI-IDS solutions achieve significant progress because they automatically process network behaviour changes for zero-day attack detection, enhance performance, and lower false alarms while speeding up response times. The framework of an adaptive intelligent detection system integrates supervised and unsupervised learning and anomaly detection and classification models in its learning mechanism. AI-IDS outperforms traditional IDS systems when testing NSL-KDD and CICIDS2017 datasets in environments with challenging network traffic through better speed and precision. The study finds adaptive AI equipment as operative cybersecurity protection tools while demonstrating future developments in federated Learning and modelling constant improvement to enhance these solutions.

Keywords

Adaptive AI, Intrusion Detection System (IDS), Real-Time Threat Response, Cybersecurity, Machine Learning.

Citations

IRE Journals:
Nageshwar Masakapalli "Adaptive AI-Driven Intrusion Detection Systems: Enhancing Threat Response in Real Time" Iconic Research And Engineering Journals Volume 7 Issue 6 2023 Page 487-497

IEEE:
Nageshwar Masakapalli "Adaptive AI-Driven Intrusion Detection Systems: Enhancing Threat Response in Real Time" Iconic Research And Engineering Journals, 7(6)