As Open radio access networks(O-RAN) shifts toward microservice-based disaggregation, learning-enabled xApps now shoulder near-real-time tasks such as interference classification that must react within tens of milliseconds. Hybrid quantum-classical models are a potential fit for that workload because expressive quantum feature maps can be paired with lightweight classical heads to deliver low-latency, energy-efficient inference as the hardware matures. Yet the same variational circuits remain vulnerable to RF adversaries: input perturbations collapses the quantum decision boundary, while parameter-space attacks silently corrupt circuit weights. We present$Q$-Sentinel, a quantum-fidelity aware robust stack that unifies (i) quantum state transformation guided by trusted manifolds, (ii) fidelity-based decision-boundary reinforcement, and (iii) sentinel snapshots that monitor cosine drift and trigger auto-repair of the variational (fusion-inclusive) parameters. We also build a quantum-aware adversarial training (QAT) baseline that applies QC-FGSM/PGD to both spectrogram inputs and quantum encodings. Evaluating with the public dataset SOI-vs-CWI, Q-Sentinel sustains 98.2 % clean accuracy, raises worst-case QC-FGSM/QC-PGD accuracy to 84.7 % / 73.6 % at$\epsilon=0.1$, and retains 70.8 % accuracy under QCPoison while capping mean parameter drift at$1.8 \times 10^{-2}$less than half that of the undefended model. These results indicate that future quantum-assisted O-RAN deployments will require defenses that preserve quantum-state geometry on Hilbert manifolds and continuously repair compromised circuits, extending beyond input-only adversarial training.
As Open radio access networks(O-RAN) shifts toward microservice-based disaggregation, learning-enabled xApps now shoulder near-real-time tasks such as interference classification that must react within tens of milliseconds. Hybrid quantum-classical models are a potential fit for that workload because expressive quantum feature maps can be paired with lightweight classical heads to deliver low-latency, energy-efficient inference as the hardware matures. Yet the same variational circuits remain vulnerable to RF adversaries: input perturbations collapses the quantum decision boundary, while parameter-space attacks silently corrupt circuit weights. We presentQ-Sentinel, a quantum-fidelity aware robust stack that unifies (i) quantum state transformation guided by trusted manifolds, (ii) fidelity-based decision-boundary reinforcement, and (iii) sentinel snapshots that monitor cosine drift and trigger auto-repair of the variational (fusion-inclusive) parameters. We also build a quantum-aware adversarial training (QAT) baseline that applies QC-FGSM/PGD to both spectrogram inputs and quantum encodings. Evaluating with the public dataset SOI-vs-CWI, Q-Sentinel sustains 98.2 % clean accuracy, raises worst-case QC-FGSM/QC-PGD accuracy to 84.7 % / 73.6 % atϵ=0.1, and retains 70.8 % accuracy under QCPoison while capping mean parameter drift at1.8×10−2less than half that of the undefended model. These results indicate that future quantum-assisted O-RAN deployments will require defenses that preserve quantum-state geometry on Hilbert manifolds and continuously repair compromised circuits, extending beyond input-only adversarial training.
As open radio access networks (O-RAN) progress into an intelligence-driven era, artificial intelligence (AI)-powered core functions and applications have recently attracted much attention. The AI-driven techniques enable near-real-time tasks such as signal interference classification for large-scale networks. Accordingly, accurate identification of interference types enables more effective successive interference cancellation, reducing performance degradation and strengthening reliability in O-RAN-based mobile networks. Since quantum computing remains energy-intensive and limited by current hardware capabilities, hybrid quantum–classical machine learning offers an efficient alternative. However, adversarial robustness and explainability remain critical challenges for such hybrid models, as emerging perturbation-based attacks can easily distort their decision boundaries. This work presentsQ-SHIELD, a quantum-assisted defense framework that enhances robustness and explainability via trusted-manifold-guided quantum state transformations and fidelity-based boundary reinforcement. Q-SHIELD is evaluated under various poisoning attacks and adversarial attacks. Using a public dataset from real O-RAN testbeds, Q-SHIELD attains 98.2% accuracy in common cases and maintains 84.7% accuracy in worst-case conditions, even under strong adversarial attacks, e.g., quantum projected gradient descent. For explainability, Q-SHIELD emphasizes causal compactness, achieving a drift correlation of 0.988 and sufficiency/comprehensiveness scores of 0.871/0.007 on the top 20% features. These results outperform adversarial-training baselines by up to 35% in defense performance. The results show that Q-SHIELD can deliver robust quantum-assisted services for the intelligent O-RAN.
Quantum machine learning (QML) is emerging as a key enabler of next-generation artificial intelligence (AI), offering more compact models and enhanced data processing capabilities. However, the integration of QML into AI-enabled network services can introduce new adversarial vulnerabilities, particularly the interface between classical encoders and quantum variational circuits. In this work, we investigate the susceptibility of QML-assisted signal classifiers to adversarial threats in the open radio access network (O-RAN) platforms. We introduce a new family of adversarial attacks, including a novel hybrid quantum-classical poisoning method (QC-Poison), along with hybrid gradient-based attacks (QC-FGSM and QC-PGD). QC-Poison induces long-term misclassification by injecting subtle adversarial, accumulating perturbations in the classical input space that propagate through the quantum encoder, effectively drifting the model’s decision boundary. Evaluation results show that QC-FGSM perturbs inputs based on the hybrid model’s gradients, reducing accuracy from 95.5% to 55.8%, while QC-PGD shows model’s performance reduction to 16.0% by iteratively corrupting quantum circuit parameters via loss maximization. QC-Poison achieves 23.9% accuracy under tight perturbation constraints without accessing training data or internal quantum parameters. The results expose critical blind spots in existing hybrid QML models that can be extended to AI-based features in the O-RAN core services. The study underscores the need for robust quantum-aware defenses that can mitigate stealthy adversarial attacks in distributed and QML-assisted applications in intelligent RAN.
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.
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.
The integration of quantum machine learning (QML) within open radio access network (O-RAN) architectures presents a promising frontier for enhancing interference classification and optimizing various 6G network use cases. We introduce a novel hybrid quantum-classical neural network (HQCNN) design that addresses critical challenges in noisy intermediate-scale quantum (NISQ) environments through an innovative feature preprocessing pipeline. By integrating deep convolutional feature extraction via ResNet-18 with principal component analysis (PCA)-based dimensionality reduction, we develop a robust computational framework that mitigates quantum gate errors and enhances computational stability. However, despite these advancements, HQCNNs remain vulnerable to adversarial attacks. Traditional classical backdoor methods are ineffective in the quantum setting due to NISQ noise and gate synthesis complexities, while existing quantum attack techniques suffer from a lack of selectivity and adaptability, making them easy to detect. To address this, we introduce Q-Poison, a novel stealthy attack that leverages parameterized quantum gates to significantly enhance attack success rates. This attack induces systematic misclassification of trigger inputs while maintaining 54.5% clean data accuracy, compared to 78.5% without attack. Our results demonstrate a substantial 1.44-fold reduction in accuracy, highlighting the need for robust defense mechanisms in quantum-enabled networks.
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.