Quantum machine learning (QML) provides a promising framework for leveraging quantum-mechanical effects in learning tasks. However, its vulnerability to adversarial perturbations remains a major challenge for practical deployment. In QML systems, small perturbations applied to classical inputs can propagate through the quantum encoding stage and distort the resulting quantum state, thereby degrading model performance. In this work, we propose a defense mechanism that replaces the conventional quantum encoding stage of a QML model with passive steering-based controlled state preparation, which guides the encoded state toward a controlled intermediate state. By tuning the steering strength and the number of steering iterations, the proposed method suppresses the influence of adversarial perturbations while maintaining high clean accuracy and improving adversarial accuracy. Experimental results demonstrate that the passive steering-based defense consistently improves adversarial accuracy across different QML models and datasets under gradient-based adversarial attacks, achieving adversarial accuracy improvements of up to 40.19%.
Quantum machine learning (QML) provides a promising framework for leveraging quantum-mechanical effects in learning tasks. However, its vulnerability to adversarial perturbations remains a major challenge for practical deployment. In QML systems, small perturbations applied to classical inputs can propagate through the quantum encoding stage and distort the resulting quantum state, thereby degrading model performance. In this work, we propose a defense mechanism that replaces the conventional quantum encoding stage of a QML model with passive steering-based controlled state preparation, which guides the encoded state toward a controlled intermediate state. By tuning the steering strength and the number of steering iterations, the proposed method suppresses the influence of adversarial perturbations while maintaining high clean accuracy and improving adversarial accuracy. Experimental results demonstrate that the passive steering-based defense consistently improves adversarial accuracy across different QML models and datasets under gradient-based adversarial attacks, achieving adversarial accuracy improvements of up to 40.19%.
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) 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.
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.
Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make mistakes. Quantum machine learning models are also vulnerable to such adversarial attacks, especially in image classification using variational quantum classifiers. While there are promising defenses against these adversarial perturbations, such as training with adversarial samples, they face practical limitations. For example, they are not applicable in scenarios where training with adversarial samples is either not possible or can overfit the models on one type of attack. In this paper, we propose an adversarial training-free defense framework that utilizes a quantum autoencoder to purify the adversarial samples through reconstruction. Moreover, our defense framework provides a confidence metric to identify potentially adversarial samples that cannot be purified the quantum autoencoder. Extensive evaluation demonstrates that our defense framework can significantly outperform state-of-the-art in prediction accuracy (up to 68%) under adversarial attacks.
This project presents a scoping review titled Adversarial Robustness in Quantum Machine Learning: A Scoping Review. The purpose of the study is to systematically map and synthesize empirical research on adversarial robustness in quantum machine learning (QML), an emerging field at the intersection of quantum computing and artificial intelligence. As QML systems move closer to real-world deployment, understanding their vulnerability to adversarial attacks and the effectiveness of proposed defenses becomes critical for ensuring reliability and security. Following the PRISMA-ScR framework, this review analyzes 53 empirical studies published between 2020 and 2026 across major databases including Scopus, ACM, IEEE Xplore, and MDPI. The study examines six key dimensions: (1) adversarial threat vectors investigated in QML, (2) QML model families evaluated under attack, (3) defense strategies proposed to enhance robustness, (4) robustness evaluation methods employed, (5) practical and technological constraints influencing research, and (6) future research directions identified in the literature. Expected outcomes include a structured taxonomy of adversarial threats in QML, a comparative mapping of defense mechanisms, identification of methodological gaps, and clarification of hardware and scalability constraints affecting robustness research. The review aims to provide a consolidated evidence base to guide future research, support the development of standardized benchmarking practices, and inform the design of more secure and scalable QML systems suitable for deployment in high-risk domains such as cybersecurity and healthcare.
Quantum machine learning (QML) is emerging as an application of quantum computing with the potential to deliver quantum advantage, but its realization for practical applications remains impeded by challenges. Among these, a key barrier is the computationally expensive task of encoding classical data into a quantum state, which could erase any prospective speedups over classical algorithms. In this study, we implement methods for the efficient preparation of quantum states representing encoded image data using variational, genetic, and matrix product state algorithms. Our results show that these methods can approximately prepare states to a level suitable for QML using circuits 2 orders of magnitude shallower than a standard state preparation implementation, thus drastically reducing circuit depth and gate count without unduly sacrificing classification accuracy. Additionally, the QML models trained and evaluated on approximately encoded data displayed an increased robustness to adversarially generated input data perturbations. This partial alleviation of adversarial vulnerability, made possible by the retention of the meaningful large-scale features of the data despite the “drowning out” of adversarial perturbations, constitutes a considerable benefit for approximate state preparation in addition to lessening the requirements of the quantum hardware. Our results, based on simulations and experiments on IBM quantum devices, highlight a promising pathway for the future implementation of accurate and robust QML models on complex datasets relevant for practical applications, bringing the possibility of NISQ-era QML advantage closer to reality.