D.PAULRAJ

Abstract

A secure and scalable approach to intrusion detection in modern networks is required due to the rapid development of cyber threats and quantum computing. Traditional security mechanisms struggle to handle the increasing complexity of cyberattacks, making Artificial Intelligence (AI)-driven Intrusion Detection Systems (IDS) a crucial defense strategy. However, AI-based IDS alone may not be sufficient against post-quantum threats, which can break conventional encryption schemes. A hybrid intrusion detection framework that incorporates post-quantum cryptography (PQC) for secure communications and makes use of machine learning for real-time anomaly detection is the subject of this study. The AI model is trained on large-scale network traffic data to detect zero-day attacks, advanced persistent threats (APTs), and insider threats with high accuracy. Meanwhile, PQC ensures resilience against potential decryption by quantum computers, safeguarding data integrity and confidentiality. O