Sparse optimisation and quantum-inspired encoding for ransomware detection

Elodie Mutombo Ngoie; Mike Wa Nkongolo

Paper 2026/520

Sparse optimisation and quantum-inspired encoding for ransomware detection

Elodie Mutombo Ngoie

, University of Pretoria

Mike Wa Nkongolo

, University of Pretoria, University of Quebec at Montreal

Abstract

Ransomware remains a persistent cybersecurity threat difficult to detect due to high-dimensional network traffic and sophisticated obfuscation techniques. Existing feature selection methods often struggle with redundancy, noise, and the curse of dimensionality, leading to poor generalisation and limited interpretability in ransomware detection. To address these challenges, we propose BioSparse-MCP, a hybrid feature selection framework that integrates gradient-based optimisation with the Minimax Concave Penalty (MCP) to enforce sparsity, alongside a Rotated Circular Partitioning (RCP) strategy to improve the spatial organisation of selected features. This design reduces redundancy, enhances discriminative power, and provides rotation-aware representations that overcome the limitations of conventional dimensionality reduction. The framework further incorporates a Quantum Feature Mapping (QFM)-inspired geometric transformation, in which features are projected onto a spherical space, rotated, and partitioned into angular sectors, while preserving linear computational complexity. All RCP and QFM operations are classically simulated, ensuring compatibility with conventional machine learning pipelines and real-time deployment without specialised hardware. Implemented in Python using standard numerical libraries, BioSparse-MCP was evaluated on 149,043 network traffic instances with an ensemble of KNN and LSTM models. The approach achieved high detection accuracy with a low False Positive Rate (0.25%). Feature attribution analysis highlights cryptocurrency addresses, threat signatures, and IP-level features as key contributors. These results demonstrate that combining sparse optimisation with quantum-inspired geometric encoding provides an efficient and interpretable solution for ransomware detection in high-dimensional network environments.

Note: Dataset and code: @misc{dr__mike_nkongolo_wa_nkongolo_2023, title={UGRansome dataset}, url={https://www.kaggle.com/dsv/7172543}, DOI={10.34740/KAGGLE/DSV/7172543}, publisher={Kaggle}, author={Dr. Mike Nkongolo Wa Nkongolo}, year={2023} }

Metadata

Available format(s): PDF
Category: Attacks and cryptanalysis
Publication info: Preprint.
Keywords: Quantum feature mapping Sparse Optimisation Minimax Concave Penalty Circular Partitioning Machine Learning XAI
Contact author(s): u22608754 @ tuks co za
mike wankongolo @ up ac za
History: 2026-03-15: approved; 2026-03-14: received; See all versions
Short URL: https://ia.cr/2026/520
License: CC BY

BibTeX

@misc{cryptoeprint:2026/520,
      author = {Elodie Mutombo Ngoie and Mike Wa Nkongolo},
      title = {Sparse optimisation and quantum-inspired encoding for ransomware detection},
      howpublished = {Cryptology {ePrint} Archive, Paper 2026/520},
      year = {2026},
      url = {https://eprint.iacr.org/2026/520}
}