article · International Journal of Computer Applications
Hybrid post-quantum cryptographic systems combine post-quantum algorithms with conventional symmetric encryption to prepare secure communications for future quantum computing threats. Finding the right configurations requires balancing security strength against performance efficiency in practical operating conditions. A controlled experimental environment evaluated combinations of CRYSTALS-Kyber key encapsulation variants and Advanced Encryption Standard key sizes across varied computational and network settings. Recorded metrics included encryption and decryption latency, network latency, throughput, and processor utilisation. Multiple machine learning models, including Random Forest, LightGBM, and neural networks, were trained to predict these performance trends. While models such as Random Forest and LightGBM demonstrated lower error rates for select metrics, overall predictive accuracy across tasks remained weak. The results demonstrate that performance in hybrid post-quantum setups involves complex, variable interactions that standard supervised learning models struggle to capture using basic feature sets.
Transitioning modern digital communications to quantum-resistant standards requires understanding how new cryptographic combinations behave in real systems. By testing whether machine learning can reliably forecast operational overheads such as latency and processor load, this research highlights the difficulty of automating system configuration and shows that simpler predictive models cannot yet replace empirical performance benchmarking.
This research represents early-stage exploratory research relevant to developers and security engineers planning migrations to post-quantum cryptography. The findings do not offer a finished commercial product, but they inform future tool design by revealing that standard machine learning approaches cannot yet reliably automate configuration selection. Practical application remains distant until more sophisticated modelling techniques or richer feature sets are developed and validated.
AI-generated from the published abstract. Always read the original work before citing.
Selecting suitable parameter configurations in hybrid postquantum cryptographic systems is not only a matter of security strength but also of performance efficiency under varying system and network conditions.Many existing studies focus mainly on security guarantees, with limited attention to how different configurations behave in real deployment environments.This creates a gap in understanding how to balance security requirements with practical performance.This study explores the use of machine learning as a data-driven approach to analyze and predict performance trends in a hybrid cryptographic system that combines CRYSTALS-Kyber (a lattice-based post-quantum key encapsulation mechanism) with the Advanced Encryption Standard (AES).A controlled environment for the experimental was developed using Pythonbased tools.Multiple configurations of AES key sizes (128, 192, 256 bits) and Kyber variants (Kyber512, Kyber768, Kyber1024) were evaluated under different network and computational conditions.The dataset result captured key performance metrics such as network latency, encryption latency, decryption latency, throughput, and CPU utilisation.Different machine learning models, including Random Forest, XGBoost, Linear Regression, Decision Tree, LightGBM, and Multilayer Perceptron (MLP), were trained and evaluated using MAE, RMSE, and R² metrics.The results show that while some models, particularly Random Forest and LightGBM, achieved relatively lower prediction errors for certain metrics, the overall predictive strength across tasks remained weak, with most R² values close to zero or negative.This indicates that the performance behaviour of the hybrid cryptographic system is influenced by complex and highly variable interactions that are not easily captured using standard supervised learning models and the current feature set.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.5120/ijca439a9afde953
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
