Sarcouncil Journal of Applied Sciences Aims & Scope

Abstract: Public-key encryption is a key component of cryptographic infrastructures, and large-scale quantum machines could break them, creating a challenge to current cryptographic systems. Network telemetry analysis and vulnerability detection of existing enterprise communication systems form the basis for this research, which explores a data-centric artificial intelligence (AI) framework for supporting the transition to post-quantum cryptography (PQC). The idea is not just to optimize the model, but to focus on acquiring, curating, and preprocessing data of high quality to ensure that the generated insights from AI-powered security analysis are accurate. The framework can be used to analyze massive amounts of network traffic data and identify features that are relevant to encrypted communication flows. It also classifies legacy cryptographic protocols and detects those that need to be migrated to quantum-resistant alternatives. The approach is designed for the Noisy Intermediate-Scale Quantum (NISQ) era, using classical AI and data mining techniques to address the current challenges of quantum hardware and future quantum threats. It shows that well filtered telemetry data can boost the performance of machine learning algorithms, can be leveraged for the proactive cryptographic risk analysis, and can be used for strategic implementation of post-quantum security mechanisms. The importance of data-centric AI as a tangible approach to bolstering cyber security against new quantum-based threats is emphasized.