Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2610.26240

Q-MALDetect: Quantum Image-Based Malware Detection and Adversarial Robustness Analysis

Walid El Maouaki, Mohammad Izen, Nouhaila Innan, Alberto Marchisio, Muhammad Shafique

On Aqora:Muhammad ShafiqueMuhammad Shafique
cs.CRquant-phSubmitted Oct 19, 2026• Announced Oct 20, 2026
arXivHTMLPDF

Abstract

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.

AI Summary

Q-MALDetect studies adversarial robustness of a hybrid quantum–classical malware detector under image-space perturbations and executable-aware binary mutations. It maps the first 50,176 bytes of x86-64 ELF files to images and combines a CNN with a four-qubit variational circuit. Experiments use 1,200 training binaries and a separate 100-malware attack holdout, comparing gradient attacks, Grad-CAM-guided NOP insertion with random or Q-learning action selection, adversarial training, and autoencoder preprocessing. Training accuracy is $97.2\%$. Undefended attack success rates (ASRs) are $42.3\%$ for FGSM, $52.3\%$ for PGD, and $78.7\%$ for sequential FGSM–PGD. The sequential attack permits up to twice the nominal displacement, so it is not a matched-budget comparison. Executable-aware ASRs are $32.9\%$ for random NOP insertion and $29.8\%$ for Q-learning, conditional on successful reconstruction. Adversarial training reduces these five rates to $5.0\%$, $5.7\%$, $34.0\%$, $9.0\%$, and $7.7\%$, respectively. Autoencoder preprocessing reduces image-space ASR but increases executable-aware ASR to $39.7\%$ and $37.2\%$, alongside increased Grad-CAM attribution within the mutable code section. Ablations find no monotonic robustness trend with qubit count; encoding changes do not suppress the strongest attack. These comparisons jointly change classical bridge dimensions and quantum interfaces. Clean metrics measure training fit, not held-out classification performance; executable ASRs exclude reconstruction failures, and functionality checks comprise structural validation plus benign-utility smoke tests. Noise results use simulation, not hardware. Deployment assessment still requires matched classical comparisons and clean-performance costs of defenses.

Little sign of AI-generated textIncrementalSmall numerics onlyMissing comparisonStrong assumptions

Central claim may not hold: The executable-aware attack rates condition on successful reconstruction, and missing reconstruction coverage prevents recovery or comparison of overall evasion rates across defenses. The reported validation establishes structural validity of reconstructed malware but does not establish preservation of malicious behavior, weakening the interpretation of the results as functionality-preserving malware evasion.

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Comments
8 pages, 10 figures, 1 table. Accepted at the 2026 IEEE 2nd International Conference on Quantum Artificial Intelligence (QAI 2026), Nottingham, UK

Related papers

Towards Robust Quantum Machine Learning

Saeefa Rubaiyet Nowmi, Jesus Lopez, Md Mahmudul Alam Imon +3 more

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.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•2 citations

Adversarially Robust Quantum-Classical Neural Network for Malware Detection

Kathan P. Vyas, Dev K. Patel, Rahul Tanna +1 more

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.

•May 22, 2026•0 citations

SoK: Critical Evaluation of Quantum Machine Learning for Adversarial Robustness

Saeefa Rubaiyet Nowmi, Jesus Lopez, Md Mahmudul Alam Imon +2 more

Quantum Machine Learning (QML) integrates quantum computational principles into learning algorithms, offering the potential for improved representational capacity and computational efficiency. Nevertheless, the security and robustness of QML systems remain largely underexplored, particularly under adversarial conditions. We present the first comprehensive systematization of adversarial robustness in QML, integrating conceptual organization with empirical evaluation across black-, gray-, and white-box threat models. We implement five representative attacks across all three threat models: a label-flipping data poisoning attack under blackbox; an encoder-level indiscriminate data poisoning attack and a proxy-model-based clean-label backdoor attack under gray-box; and a circuit-level backdoor attack (QTrojan) and gradient-based evasion attacks (FGSM and PGD) under whitebox. We evaluate the attacks using a Quantum Multilayer Perceptron (QMLP) trained on MNIST and AZ-Class across circuit depths of 2, 5, 10 and 50 layers and two encoding schemes (angle and amplitude). Our extensive evaluations reveal a fundamental accuracy-robustness trade-off. In particular, amplitude encoding yields the highest clean accuracy (92.6 % on MNIST, 67% on AZ-Class); however, it collapses under adversarial perturbations and depolarizing noise, while shallow angle-encoded models remain substantially more stable. In addition, QUID is highly effective under noiseless conditions but is weakened by noise, whereas the proxy-model backdoor persists unless the circuit itself is overwhelmed, highlighting that noise is an asymmetric and unreliable passive defense. Furthermore, the circuit-level backdoor fails in the multi-class setting, indicating a scalability constraint. Finally, QMLP models are more robust than Classical Multi-Layer Perceptron (CMLP) models under label-flipping attacks but are substantially more vulnerable to gradient-based evasion, motivating the need for quantumspecific defenses. We conclude by proposing a threat-aware, noise-resilient design framework for secure and robust QML deployment.

arXiv:2511.14989•IEEE Symposium on Security and Privacy (S&P)•May 18, 2026•5 citations

Adversarial Robustness in Quantum Machine Learning: A Scoping Review

Yanche Ari Kustiawan, Khairil Imran Ghauth

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.

Computers•Apr 9, 2026•3 citations

Towards Quantum Machine Learning for Malicious Code Analysis

Jesus Lopez, Saeefa Rubaiyet Nowmi, Viviana Cadena +1 more

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.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•2 citations

Quantum-Enhanced Adversarial Defense: A Hybrid Machine Learning Framework for Post-Quantum Cybersecurity

Sumanth Banakar, Jaya Madhava Sai Teja Kosireddy, Justin Davis +3 more

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.

EPJ Web of Conferences•Jan 1, 2026•1 citation
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.
Q-MALDetect studies adversarial robustness of a hybrid quantum–classical malware detector under image-space perturbations and executable-aware binary mutations. It maps the first 50,176 bytes of x86-64 ELF files to images and combines a CNN with a four-qubit variational circuit. Experiments use 1,200 training binaries and a separate 100-malware attack holdout, comparing gradient attacks, Grad-CAM-guided NOP insertion with random or Q-learning action selection, adversarial training, and autoencoder preprocessing.
Training accuracy is 97.2%97.2\%97.2%. Undefended attack success rates (ASRs) are 42.3%42.3\%42.3% for FGSM, 52.3%52.3\%52.3% for PGD, and 78.7%78.7\%78.7% for sequential FGSM–PGD. The sequential attack permits up to twice the nominal displacement, so it is not a matched-budget comparison. Executable-aware ASRs are 32.9%32.9\%32.9% for random NOP insertion and 29.8%29.8\%29.8% for Q-learning, conditional on successful reconstruction. Adversarial training reduces these five rates to 5.0%5.0\%5.0%, 5.7%5.7\%5.7%, 34.0%34.0\%34.0%, 9.0%9.0\%9.0%, and 7.7%7.7\%7.7%, respectively. Autoencoder preprocessing reduces image-space ASR but increases executable-aware ASR to 39.7%39.7\%39.7% and 37.2%37.2\%37.2%, alongside increased Grad-CAM attribution within the mutable code section.
Ablations find no monotonic robustness trend with qubit count; encoding changes do not suppress the strongest attack. These comparisons jointly change classical bridge dimensions and quantum interfaces. Clean metrics measure training fit, not held-out classification performance; executable ASRs exclude reconstruction failures, and functionality checks comprise structural validation plus benign-utility smoke tests. Noise results use simulation, not hardware. Deployment assessment still requires matched classical comparisons and clean-performance costs of defenses.
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 the potential for improved representational capacity and computational efficiency. Nevertheless, the security and robustness of QML systems remain largely underexplored, particularly under adversarial conditions. We present the first comprehensive systematization of adversarial robustness in QML, integrating conceptual organization with empirical evaluation across black-, gray-, and white-box threat models. We implement five representative attacks across all three threat models: a label-flipping data poisoning attack under blackbox; an encoder-level indiscriminate data poisoning attack and a proxy-model-based clean-label backdoor attack under gray-box; and a circuit-level backdoor attack (QTrojan) and gradient-based evasion attacks (FGSM and PGD) under whitebox. We evaluate the attacks using a Quantum Multilayer Perceptron (QMLP) trained on MNIST and AZ-Class across circuit depths of 2, 5, 10 and 50 layers and two encoding schemes (angle and amplitude). Our extensive evaluations reveal a fundamental accuracy-robustness trade-off. In particular, amplitude encoding yields the highest clean accuracy (92.6 % on MNIST, 67% on AZ-Class); however, it collapses under adversarial perturbations and depolarizing noise, while shallow angle-encoded models remain substantially more stable. In addition, QUID is highly effective under noiseless conditions but is weakened by noise, whereas the proxy-model backdoor persists unless the circuit itself is overwhelmed, highlighting that noise is an asymmetric and unreliable passive defense. Furthermore, the circuit-level backdoor fails in the multi-class setting, indicating a scalability constraint. Finally, QMLP models are more robust than Classical Multi-Layer Perceptron (CMLP) models under label-flipping attacks but are substantially more vulnerable to gradient-based evasion, motivating the need for quantumspecific defenses. We conclude by proposing a threat-aware, noise-resilient design framework for secure and robust 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%\mathbf{9 5 - 9 6 \%}95−96%on API-Graph, 91-92% on AZ-Domain, and77%\mathbf{7 7 \%}77%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.