Classical machine learning (CML) has been extensively studied for malware classification. With the emergence of quantum computing, quantum machine learning (QML) presents a paradigm-shifting opportunity to improve malware detection, though its application in this domain remains largely unexplored. In this study, we investigate two hybrid quantumclassical models - a Quantum Multilayer Perceptron (QMLP) and a Quantum Convolutional Neural Network (QCNN), for malware classification. Both models utilize angle embedding to encode malware features into quantum states. QMLP captures complex patterns through full qubit measurement and data reuploading, while QCNN achieves faster training via quantum convolution and pooling layers that reduce active qubits. We evaluate both models on five widely used malware datasets -API-Graph, EMBER-Domain, EMBER-Class, AZ-Domain, and AZ-Class, across binary and multiclass classification tasks. Our results show high accuracy for binary classification$\mathbf{9 5 - 9 6 \%}$on API-Graph, 91-92% on AZ-Domain, and$\mathbf{7 7 \%}$on EMBER-Domain. In multiclass settings, accuracy ranges from 91.6-95.7% on API-Graph, 41.7-93.6% on AZ-Class, and 60.7-88.1% on EMBER-Class. Overall, QMLP outperforms QCNN in complex multiclass tasks, while QCNN offers improved training efficiency at the cost of reduced accuracy.
Classical machine learning (CML) has been extensively studied for malware classification. With the emergence of quantum computing, quantum machine learning (QML) presents a paradigm-shifting opportunity to improve malware detection, though its application in this domain remains largely unexplored. In this study, we investigate two hybrid quantumclassical models - a Quantum Multilayer Perceptron (QMLP) and a Quantum Convolutional Neural Network (QCNN), for malware classification. Both models utilize angle embedding to encode malware features into quantum states. QMLP captures complex patterns through full qubit measurement and data reuploading, while QCNN achieves faster training via quantum convolution and pooling layers that reduce active qubits. We evaluate both models on five widely used malware datasets -API-Graph, EMBER-Domain, EMBER-Class, AZ-Domain, and AZ-Class, across binary and multiclass classification tasks. Our results show high accuracy for binary classification95−96%on API-Graph, 91-92% on AZ-Domain, and77%on EMBER-Domain. In multiclass settings, accuracy ranges from 91.6-95.7% on API-Graph, 41.7-93.6% on AZ-Class, and 60.7-88.1% on EMBER-Class. Overall, QMLP outperforms QCNN in complex multiclass tasks, while QCNN offers improved training efficiency at the cost of reduced accuracy.
Reliable detection of malware is a fundamental component of cybersecurity in the modern world. Models have to be able to identify new and sophisticated malware strains, even among large and complex datasets, while having accuracy, efficiency, and understandability. Review of previous research, based on direct comparison, of Quantum>Support Vector Machines, Quantum Neural>Networks,and hybrid modeles such-as Quantum Multilayer Perceptron is the basis of the proposed clear and concise QML framework for malware detection. Basic research by Cai et al. on QSVM demonstrates high classification accuracy. In exploration of bases, QNN has passed the trials and indicated the need for improvement due to data re-uploading. Finally, further experiments on QMLP and QCNN researched the relationship between classification accuracy and model training cost. XAI added the level of interpretability and the analysis demonstrated an O(log n) computational leverage, which is the key ingredient that maintains this field. These combinations of research construct the unified framework of the strong classification strength of QSVM, the architecture flexibility of QNN, and the insights from XAI. This leads to a more robust accuracy, explainability, and reliability of existing and future malware detection systems.
This study explores the application of quantum machine learning (QML) algorithms to enhance cybersecurity threat detection, particularly in the classification of malware and intrusion detection within high-dimensional datasets. Classical machine learning approaches encounter limitations when dealing with intricate, obfuscated malware patterns and extensive network intrusion data. To address these challenges, we implement and evaluate various QML algorithms, including Quantum Neural Networks (QNN), Quantum Support Vector Machines (QSVM), and hybrid Quantum Convolutional Neural Networks (QCNN) for malware detection tasks. Our experimental analysis utilized two datasets: the Intrusion dataset, comprising 150 samples with 56 memory-based features derived from Volatility framework analysis, and the ObfuscatedMalMem2022 dataset, containing 58,596 samples with 57 features representing benign and malicious software. Remarkably, our QML methods demonstrated superior performance compared to classical approaches, achieving accuracies of 95% for QNN and 94% for QSVM. These quantum-enhanced methods leveraged quantum superposition and entanglement principles to accurately identify complex patterns within highly obfuscated malware samples that were imperceptible to classical methods. To further advance malware analysis, we propose a novel real-time malware analysis framework that incorporates Quantum Feature Extraction using Quantum Fourier Transform, Quantum Feature Maps, and Classification using Variational Quantum Circuits. This system integrates explainable AI methods, including GradCAM++ and ScoreCAM algorithms, to provide interpretable insights into the quantum decision-making processes.
Quantum Machine Learning (QML) fuses quantum computing with machine learning to address complex tasks with potential speedups over classical methods. While QML models such as variational quantum classifiers (QVC), quantum multilayer perceptron(QMLP) models and quantum convolutional neural networks (QCNN) have demonstrated promise in applications like image recognition and malware classification, they remain vulnerable to adversarial threats. Inspired by the vulnerabilities in classical ML, this work systematically investigates how attacks-ranging from training-time poisoning and inferencetime evasion (e.g., quantum versions of FGSM and PGD) to deployment-time trigger attacks-manifest in quantum circuits. We explore how classical adversarial strategies adapt to quantum models through parameterized encodings, hybrid architectures, and probabilistic outputs. The poster evaluates different quantum classifiers under adversarial settings, comparing their robustness, trainability, and resilience to perturbations. Defense mechanisms such as randomized encoding, engineered noise channels, and quantum adversarial training are analyzed in relation to specific threat types. In addition, we assess how quantum models behave differently than classical counterparts under attack, and how quantum-specific design constraints can either exacerbate or mitigate these effects. Our ultimate goal is to define and construct robust QML systems that are both theoretically sound and practically secure. By synthesizing results across multiple QML architectures and threat models, this work provides actionable insight into the development of resilient quantum classifiers, paving the way toward trustworthy and scalable quantum machine learning.
Abstract Quantum neural network fully utilize the respective advantages of quantum computing and classical neural network, providing a new path for the development of artificial intelligence. In this paper, we propose a modified lightweight quantum convolutional neural network (QCNN), which contains a high-scalability and parameterized quantum convolutional layer and a quantum pooling circuit with quantum bit multiplexing, effectively utilizing the computational advantages of quantum systems to accelerate classical machine learning tasks. The experimental results show that the classification accuracy (precision, F1-score) of this QCNN on DataCon2020, Ember and BODMAS have been improved to 96.65% (94.3%, 96.74%), 92.4% (91.01%, 92.53%) and 95.6% (91.99%, 95.78%), indicating that this QCNN has strong robustness as well as good generalization performance for malicious code detection, which is of great significance to cyberspace security.
Multiclass classification is of great interest for various applications, for example, it is a common task in computer vision, where one needs to categorize an image into three or more classes. Here we propose a quantum machine learning approach based on quantum convolutional neural networks for solving the multiclass classification problem. The corresponding learning procedure is implemented via TensorFlowQuantum as a hybrid quantum-classical (variational) model, where quantum output results are fed to the softmax activation function with the subsequent minimization of the cross entropy loss via optimizing the parameters of the quantum circuit. Our conceptional improvements here include a new model for a quantum perceptron and an optimized structure of the quantum circuit. We use the proposed approach to solve a 4-class classification problem for the case of the MNIST dataset using eight qubits for data encoding and four ancilla qubits; previous results have been obtained for 3-class classification problems. Our results show that the accuracy of our solution is similar to classical convolutional neural networks with comparable numbers of trainable parameters. We expect that our findings will provide a new step toward the use of quantum neural networks for solving relevant problems in the NISQ era and beyond.
The rapid development of quantum machine learning (QML) has created new opportunities for malware detection and classification. However, the effectiveness of QML-based malware research depends strongly on the availability and suitability of open-source malware datasets. Although many publicly accessible malware datasets have been designed for classical machine learning, their features and limitations have not been systematically scrutinised on quantum computing grounds. This short review provides a structured overview of publicly available open-source malware datasets: EMBER (Endgame Malware BEnchmark for Research), DREBIN Android malware dataset, CIC-MalMem-2022 (Canadian Institute for Cybersecurity Malware Memory Analysis Dataset 2022), and VirusShare, and evaluates their suitability for quantum machine learning applications. The datasets are analysed based on data modality, feature representation, mode of labelling, and accessibility. Key research issues are identified, including high dimensionality, class imbalance, uncertainty of labels, and dataset bias. Particular attention is given to limitations posed by near-term quantum devices, such as qubit availability, circuit depth restrictions, and data encoding overhead. Among the reviewed datasets, DREBIN offers the most favourable characteristics for near-term QML experimentation. Its sparse binary feature structure, after reduction to a 126-feature subset or via principal component analysis (PCA) to 15 - 50 components, yields compact vectors compatible with current qubit constraints. EMBER and VirusShare present the greatest encoding challenges owing to their very high dimensionality and lack of standardised feature representations. Angle encoding and hybrid quantum-classical approaches are identified as the most practical encoding strategies for current NISQ (Noisy Intermediate-Scale Quantum) devices. A five-criterion evaluation framework, covering feature dimensionality, encoding feasibility, dataset size, label quality, and preprocessing requirements, is proposed to guide dataset selection. The findings underscore the urgent need for purpose-built benchmark datasets designed with quantum hardware constraints in mind.