Quantum machine-learning (QML) models are increasingly considered for security applications, yet their adversarial robustness in malware analysis remains insufficiently understood. This paper presents Q-MALDetect, a hybrid convolutional and variational-quantum detector for byte-image representations of x86-64 Executable and Linkable Format (ELF) binaries, and evaluates it under feature-space and a range of Grad-CAM-guided, executable-aware evasion attacks. The model achieves 97.2% training accuracy, but its robustness deteriorates as attack strength increases, with the strongest evaluated feature-space attack reaching a 78.7% attack success rate (ASR). Among executable-aware attacks, Grad-CAM-guided no-operation (NOP) insertion produces the highest conditional ASR of 32.9%. Dynamic adversarial training is the most effective evaluated defense, reducing feature-space ASR to as low as 5.0%, executable-aware ASR to 7.7%, and the sequential-attack ASR to 34.0%. In contrast, convolutional-autoencoder preprocessing increases executable-aware ASR to 39.7%, coinciding with a rise in Grad-CAM attribution mass within the mutable .text region from 35.2% to 45.7%. Ablation results reveal no monotonic relationship between qubit count and robustness, while the encoding interface modifies the learned attack surface without neutralizing the strongest attack. These findings demonstrate that the effectiveness of attacks and defenses depends strongly on the perturbation constraints and evaluation conditions. Reliable deployment of QML malware detectors therefore requires assessment against both feature-space and executable-aware attacks rather than reliance on clean accuracy or generic denoising alone.
Comments
8 pages, 10 figures, 1 table. Accepted at the 2026 IEEE 2nd International Conference on Quantum Artificial Intelligence (QAI 2026), Nottingham, UK
Quantum machine-learning (QML) models are increasingly considered for security applications, yet their adversarial robustness in malware analysis remains insufficiently understood. This paper presents Q-MALDetect, a hybrid convolutional and variational-quantum detector for byte-image representations of x86-64 Executable and Linkable Format (ELF) binaries, and evaluates it under feature-space and a range of Grad-CAM-guided, executable-aware evasion attacks. The model achieves 97.2% training accuracy, but its robustness deteriorates as attack strength increases, with the strongest evaluated feature-space attack reaching a 78.7% attack success rate (ASR). Among executable-aware attacks, Grad-CAM-guided no-operation (NOP) insertion produces the highest conditional ASR of 32.9%. Dynamic adversarial training is the most effective evaluated defense, reducing feature-space ASR to as low as 5.0%, executable-aware ASR to 7.7%, and the sequential-attack ASR to 34.0%. In contrast, convolutional-autoencoder preprocessing increases executable-aware ASR to 39.7%, coinciding with a rise in Grad-CAM attribution mass within the mutable .text region from 35.2% to 45.7%. Ablation results reveal no monotonic relationship between qubit count and robustness, while the encoding interface modifies the learned attack surface without neutralizing the strongest attack. These findings demonstrate that the effectiveness of attacks and defenses depends strongly on the perturbation constraints and evaluation conditions. Reliable deployment of QML malware detectors therefore requires assessment against both feature-space and executable-aware attacks rather than reliance on clean accuracy or generic denoising alone.
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.
The increasing sophistication of malware poses significant challenges to modern machine learning (ML) based detection systems. This has motivated growing interest in quantum and hybrid quantum-classical ML models as alternatives to improve representational efficiency and robustness. However, high sensitivity to quantum noise and limited scalability raises question on the deployment of Quantum Machine Learning (QML) models on Noisy Intermediate-Scale Quantum (NISQ) devices. To address these challenges, we propose QSLP (Quantum model with Secure Latent-space and Pixel space), a unified hybrid quantum-classical architecture for image-based malware detection that integrates robustness at both latent-space and pixel-space. QSLP integrates a novel defense mechanism, i.e., Quantum Noise Injection Class Center Perturbation (QNI-CCP) to add sensitivity-weighted perturbations into the latent space prior to the quantum circuit execution. We investigate the quantum advantage, latent-space robustness, and adversarial resilience of QSLP. Our experiments with different datasets show that integrating QNI-CCP into classical neural network (CNN) and quantum neural network (QNN) pipelines improves both generalization performance and adversarial robustness at the latent space level. Complementing this latent-space defense, adversarial training in QSLP further strengthens the model against pixel-level perturbations.
Quantum Machine Learning (QML) integrates quantum computational principles into learning algorithms, offering improved representational capacity and computational efficiency. However, the security and robustness of QML systems remain underexplored, particularly under adversarial conditions. We present the first comprehensive systematization of adversarial robustness in QML, combining conceptual organization with empirical evaluation across black-box, gray-box, and white-box threat models. We implement five representative attacks: a label-flipping poisoning attack under black-box; an encoder-level indiscriminate poisoning attack and a proxy-model clean-label backdoor attack under gray-box; and a circuit-level backdoor attack (QTrojan) and gradient-based evasion attacks (FGSM and PGD) under white-box. We evaluate these attacks using a Quantum Multilayer Perceptron (QMLP) trained on MNIST and AZ-Class across circuit depths of 2, 5, 10, and 50 layers with angle and amplitude encoding schemes. Our evaluations reveal a fundamental accuracy-robustness trade-off. Amplitude encoding achieves the highest clean accuracy (92.6% on MNIST and 67% on AZ-Class) but collapses under adversarial perturbations and depolarizing noise, whereas shallow angle-encoded models remain more stable. QUID is effective under noiseless conditions but weakened by noise, while the proxy-model backdoor persists unless the circuit itself is overwhelmed. Furthermore, the circuit-level backdoor fails in the multi-class setting, indicating a scalability limitation. Finally, QMLP models are more robust than Classical Multi-Layer Perceptron (CMLP) models under label-flipping attacks but substantially more vulnerable to gradient-based evasion. We conclude by proposing a threat-aware and noise-resilient framework for secure QML deployment.
Quantum machine learning (QML) is emerging as a promising paradigm at the intersection of quantum computing and artificial intelligence, yet its security under adversarial conditions remains insufficiently understood. This scoping review aims to systematically map empirical research on adversarial robustness in QML and to identify dominant threat models, defense strategies, evaluation approaches, practical constraints, and future research directions. Following PRISMA-ScR guidelines, four major databases were searched, resulting in 53 eligible empirical studies published between 2020 and 2026. The findings show that most research concentrates on input-level evasion attacks, particularly adversarial examples, and primarily evaluates robustness in classification-oriented models such as variational quantum circuits and quantum neural networks. Defense strategies are largely adapted from classical adversarial training and noise-based mitigation, with limited deployment on real quantum hardware. Robustness assessment is predominantly empirical, relying on accuracy degradation and attack success rate, while formal certification methods remain less common. The literature also highlights substantial constraints related to hardware limitations, NISQ noise, computational cost, and dataset scale. Overall, the evidence indicates that adversarial robustness research in QML is expanding but remains methodologically concentrated, underscoring the need for standardized benchmarking, scalable defenses, and hardware-validated robustness evaluation frameworks.
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.
The emergence of quantum computing introduces significant challenges to traditional cybersecurity mechanisms, requiring innovative approaches for post-quantum environments. The main purpose of the study is to design a Quantum-Enhanced Adversarial Defense (QEAD) framework that integrates Quantum Machine Learning (QML) with Adversarial Deep Learning (ADL) to detect both classical and quantum-level cyberattacks. The research utilizes a simulated dataset containing post-quantum attack vectors and evaluates three models: Classical Deep Learning (DL), Quantum ML, and the proposed Hybrid QEAD. The experimental results show that the Hybrid QEAD model achieves the highest detection accuracy (91.44%), outperforming Classical DL and Quantum ML in energy efficiency, with statistically significant improvements (ANOVA, p < 0.05). The quantum properties of superposition and entanglement enhance feature representation and parallel computation, resulting in faster and more accurate threat detection. To address current hardware limitations such as circuit depth and quantum noise, the framework explores practical mitigation strategies including zero-noise extrapolation (ZNE), probabilistic error cancellation (PEC), and noise-aware variational circuit training. Despite these constraints, QEAD demonstrates viable deployment potential in prequantum transition infrastructures. The findings establish QEAD as a scalable solution for post-quantum cybersecurity, with future applications in Quantum Blockchain, Federated Quantum Learning, and Quantum IoT Security.
Muhammad Shafique