Author : Venkat Garikipati and Karthick.M

The rapid advancement of cyber threats, coupled with the emergence of quantum computing, necessitates the development of robust cybersecurity frameworks. Traditional security measures are becoming insufficient in protecting cloud-based infrastructures from evolving attacks. This study proposes an AI-driven threat detection system integrated with post-quantum cryptographic techniques to enhance cybersecurity resilience. The methodology involves real-time data collection from cloud security logs, intrusion detection systems, and open-source cyber threat intelligence feeds. The collected data is pre-processed using Min-Max normalization to standardize features and improve model performance. A deep learning-based anomaly detection framework is developed using convolutional neural networks and recurrent neural networks (RNN) to identify zero-day threats. The model is trained on historical attack patterns and continuously adapts to emerging cyber threats. Additionally, post-quantum cryptographic algorithms, including lattice-based and hash-based encryption techniques, are integrated to secure AI-generated threat intelligence, ensuring data confidentiality and integrity in cloud environments. The combination of AI and quantum-resistant security techniques fortifies cloud cybersecurity against sophisticated cyber threats and quantum-enabled attacks. The proposed system was implemented in Python, utilizing TensorFlow and Scikit-Learn for deep learning, and PyCryptodome for cryptographic operations. The results demonstrate improved threat detection accuracy while reducing false positives compared to traditional cybersecurity models. Additionally, the hybrid approach enhances detection precision while minimizing computational overhead, making it suitable for real-time deployment in cloud environments. Performance evaluation shows that the AI-driven model achieved 98.6% accuracy in anomaly detection and 97.2% accuracy in zero-day threat prediction, proving its effectiveness in enhancing cybersecurity within cloud infrastructures.

Keywords: Post-Quantum Cryptography, AI-Driven Threat Detection, Cloud Security, Anomaly Detection, Cyber Threat Intelligence.