Saved in:
Bibliographic Details
Main Authors: Le, Huu Phu, Do, Phuc Hao, Nguyen, Vo Hoang Long, Van Nguyen, Nang Hung
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.07924
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916943128166400
author Le, Huu Phu
Do, Phuc Hao
Nguyen, Vo Hoang Long
Van Nguyen, Nang Hung
author_facet Le, Huu Phu
Do, Phuc Hao
Nguyen, Vo Hoang Long
Van Nguyen, Nang Hung
contents Detecting unseen ransomware is a critical cybersecurity challenge where classical machine learning often fails. While Quantum Machine Learning (QML) presents a potential alternative, its application is hindered by the dimensionality gap between classical data and quantum hardware. This paper empirically investigates a hybrid framework using a Variational Quantum Classifier (VQC) interfaced with a high-dimensional dataset via Principal Component Analysis (PCA). Our analysis reveals a dual challenge for practical QML. A significant information bottleneck was evident, as even the best performing 12-qubit VQC fell short of the classical baselines 97.7\% recall. Furthermore, a non-monotonic performance trend, where performance degraded when scaling from 4 to 8 qubits before improving at 12 qubits suggests a severe trainability issue. These findings highlight that unlocking QMLs potential requires co-developing more efficient data compression techniques and robust quantum optimization strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Non-Monotonic Relationship: An Empirical Analysis of Hybrid Quantum Classifiers for Unseen Ransomware Detection
Le, Huu Phu
Do, Phuc Hao
Nguyen, Vo Hoang Long
Van Nguyen, Nang Hung
Quantum Physics
Cryptography and Security
Detecting unseen ransomware is a critical cybersecurity challenge where classical machine learning often fails. While Quantum Machine Learning (QML) presents a potential alternative, its application is hindered by the dimensionality gap between classical data and quantum hardware. This paper empirically investigates a hybrid framework using a Variational Quantum Classifier (VQC) interfaced with a high-dimensional dataset via Principal Component Analysis (PCA). Our analysis reveals a dual challenge for practical QML. A significant information bottleneck was evident, as even the best performing 12-qubit VQC fell short of the classical baselines 97.7\% recall. Furthermore, a non-monotonic performance trend, where performance degraded when scaling from 4 to 8 qubits before improving at 12 qubits suggests a severe trainability issue. These findings highlight that unlocking QMLs potential requires co-developing more efficient data compression techniques and robust quantum optimization strategies.
title A Non-Monotonic Relationship: An Empirical Analysis of Hybrid Quantum Classifiers for Unseen Ransomware Detection
topic Quantum Physics
Cryptography and Security
url https://arxiv.org/abs/2509.07924