Smart Defense: AI-Powered Adaptive IDs for Real-Time Zero-Day Threat Mitigation

• Author(s): Mohammad Majharul Islam Jabed ; Amit Banwari Gupta ; Sharmin Akter ; Muntaha Islam ; Jannatul Ferdous
• Paper ID: 1708240
• Page: 804-815
• Published Date: 30-09-2023
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 7 Issue 3 September-2023

Abstract

Zero-day attacks have become a permanent threat to digital security systems worldwide because of continuous digital progress. Traditional intrusion detection systems (IDS) cannot detect previously unknown vulnerabilities and subsequent mitigation because their static rule-based detection systems fall short. The proposed research presents an innovative AI-based adaptive IDS framework that soldiers to target zero-day threats during real-time operations. The proposed system uses CNN, LSTM deep learning, and machine learning algorithms to detect unusual behaviors that warrant threat identification, although signature-based data is unavailable. The model received evaluation using benchmark sets consisting of NSL-KDD and CICIDS2017 while processing diverse attack patterns and standard network operations. The system implements a threat detection strategy update mechanism through continual learning methods, ensuring its ability to adapt as the threat ecosystem changes. The proposed IDS achieves superior results against conventional models by maintaining very high accuracy (97.4%) and precision (95.8%) in addition to recall (96.9%) and F1-Score (96.3%) and low false-positive rates. Real-time monitoring will not strain system infrastructure because the architecture has optimized resource utilization. Table, bar graphs, and pie charts present the analytical summary of threat recognition features, resource needs, and threat distribution types. The adaptive model design both improves quick response and decreases the need for human interaction. The research enhances existing studies about intelligent cybersecurity protections and provides applicable solutions for establishing security in public institutions, healthcare centers, and financial networks. The future development will combine blockchain authentication with federated learning protocols for protecting privacy during threat intelligence exchange. Artificial intelligence systems that learn and adapt form a significant paradigm shift toward advanced protection mechanisms that can prevent new zero-day attacks.

Keywords

Intrusion Detection System, Zero-Day Attack, Artificial Intelligence, Cybersecurity, Real-Time Threat Detection

Citations

IRE Journals:
Mohammad Majharul Islam Jabed , Amit Banwari Gupta , Sharmin Akter , Muntaha Islam , Jannatul Ferdous "Smart Defense: AI-Powered Adaptive IDs for Real-Time Zero-Day Threat Mitigation" Iconic Research And Engineering Journals Volume 7 Issue 3 2023 Page 804-815

IEEE:
Mohammad Majharul Islam Jabed , Amit Banwari Gupta , Sharmin Akter , Muntaha Islam , Jannatul Ferdous "Smart Defense: AI-Powered Adaptive IDs for Real-Time Zero-Day Threat Mitigation" Iconic Research And Engineering Journals, 7(3)