Machine Learning Enhanced Quantum-Safe Encryption: A Novel Optimisation Framework

The standardisation of post-quantum cryptography (PQC) by NIST marks a critical transition away from classical public-key schemes towards quantum-resistant successors. As machine learning (ML) applications proliferate, the demand for efficient cryptographic primitives intensifies, requiring implementations that are simultaneously quantum-safe and resource-aware. Recent surveys have investigated the interplay between ML and PQC, with particular focus on ML-assisted parameter optimisation, privacy-preserving ML leveraging lattice-based cryptography, and neural-network implementations of quantum-resistant algorithms. Building on these findings, we propose QSafe-ML, a comprehensive four-stage framework that integrates hardware profiling, surrogate modelling via ML, constrained multi-objective optimisation, and continuous security validation to facilitate the tuning of PQC parameters and implementations. The framework targets NIST-standardised lattice-based schemes CRYSTALS-Kyber, CRYSTALS-Dilithium, Falcon, and NTRU across three heterogeneous hardware platforms. Experimental evaluation with n=30 repeated trials demonstrates mean latency reductions of 27.5–41.9% (95% CI ±1.1–1.7 pp), memory savings of 13.3–30.2%, and energy savings of 22.8–38.2% over NIST reference baselines, with all configurations maintaining ≥128-bit post-quantum security. An ablation study confirms that surrogate-guided search accounts for the dominant share of these gains. All code, data, and benchmark instructions are released at a public repository (available upon acceptance of this manuscript) to promote reproducibility in evaluating ML-assisted cryptographic systems.