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

IEEE Internet of Things Journal

Verifiable Quantum Machine Learning Inference Consistency for Classical Clients in Noisy Quantum Clouds

Seungkwon Lee, Seok Bin Son, Chaeyeon Kim, Joongheon Kim, Hoh Peter In

Published Aug 31, 2026• 0 citations
Publisher

Abstract

Quantum machine learning (QML) is an emerging paradigm that aims to achieve high expressive power by leveraging quantum advantage. However, realizing these advantages in practice inevitably requires executing inference on remote, noisy quantum hardware. Such hardware produces probabilistic and non-reproducible outcomes, leaving classical users without a principled way to verify reported results. We proposezkQML, the first framework that enables a fully classical verifier to certify that a reported QML inference result is consistent with a committed model up to a device-calibrated noise tolerance, by leveraging zero-knowledge succinct non-interactive argument of knowledge (zk-SNARKs). zkQML arithmetizes the ideal semantics of quantum inference and enforces consistency using cryptographic zk-SNARKs, while explicitly accounting for device noise through a noise-bounded correctness notion. Experiments on both simulators and real quantum hardware show that the proposed arithmetic modeling closely matches ideal quantum inference and enables verifier-efficient verification with small proof sizes and near-constant verification time. These results demonstrate that zkQML provides a practical and sound foundation for trustworthy quantum inference in realistic, non-reproducible execution environments.

DOI
10.1109/jiot.2026.3728808

Related papers

zkQML: Verifiable and Privacy-Preserving Inference for Quantum Machine Learning (Student Abstract)

Seung Kwon Lee, Seok Bin Son, Joongheon Kim +1 more

Quantum machine learning (QML) has attracted growing interest for their ability to achieve superior performance with significantly fewer parameters. However, the high cost and scarcity of current hardware push inference to cloud-hosted quantum devices, creating a tension between verifiability and confidentiality. This work proposes a novel framework that converts quantum neural network operations into classical arithmetic circuits that faithfully approximate genuine quantum computations. By encrypting these circuits with zero-knowledge proofs, it ensures computational validity while concealing internal parameters. Experimental results show that our classical circuits achieve fidelity above 0.9996 and total variation distance below 1% compared to actual quantum computations, verifying the practicality of trustworthy and privacy-preserving quantum inference.

Proceedings of the AAAI Conference on Artificial Intelligence•Mar 14, 2026•3 citations

Verifying Adversarial Robustness in Quantum Machine Learning: from theory to physical validation via a software tool

Ji Guan, Mingsheng Ying

As with classical neural networks, quantum machine learning (QML) models are vulnerable to small input perturbations that can significantly alter output predictions. Certifying the robustness of QML models, particularly on NISQ hardware, is therefore a fundamental step toward trustworthy quantum AI. This chapter reviews our recently developed comprehensive formal framework for verifying adversarial robustness in QML. The core of this framework is a fidelity-based robustness lower bound computable directly from the measurement outcome distribution, which enables both formal verification and empirical estimation on real quantum devices. Additionally, the optimal bound can be computed via semidefinite programming (SDP) with full knowledge of the quantum machine learning models. We incorporate these results into: (1) an efficient formal verification framework; (2) VeriQR, the first dedicated QML robustness verification tool; and (3) the first experimental benchmark of quantum adversarial robustness on a 20-qubit superconducting processor. Together, these systematic advances enable scalable, physically grounded robustness evaluation of QML models.

quant-pharXiv:2605.29877•Quantum science and technology•May 29, 2026•0 citations

A obustness fication Tool for uantum Machine Learning Models

Yanling Lin, Ji Guan, Wang Sheng Fang +2 more

Abstract Adversarial noise attacks present a significant threat to quantum machine learning (QML) models, similar to their classical counterparts. This is especially true in the current Noisy Intermediate-Scale Quantum era, where noise is unavoidable. Therefore, it is essential to ensure the robustness of QML models before their deployment. To address this challenge, we introduce VeriQR, the first tool designed specifically for formally verifying and improving the robustness of QML models, to the best of our knowledge. This tool mimics real-world quantum hardware’s noisy impacts by incorporating random noise to formally validate a QML model’s robustness. VeriQR supports exact (sound and complete) algorithms for both local and global robustness verification. For enhanced efficiency, it implements an under-approximate (complete) algorithm and a tensor network-based algorithm to verify local and global robustness, respectively. As a formal verification tool, VeriQR can detect adversarial examples and utilize them for further analysis and to enhance the local robustness through adversarial training, as demonstrated by experiments on real-world quantum machine learning models. Moreover, it permits users to incorporate customized noise. Based on this feature, we assess VeriQR using various real-world examples, and experimental outcomes confirm that the addition of specific quantum noise can enhance the global robustness of QML models. These processes are made accessible through a user-friendly graphical interface provided by VeriQR, catering to general users without requiring a deep understanding of the counter-intuitive probabilistic nature of quantum computing.

Lecture notes in computer science•Sep 10, 2024•5 citations

Trustworthy Quantum Machine Learning: A Roadmap for Reliability, Robustness, and Security in the NISQ Era

Ferhat Ozgur Catak, Jungwon Seo, Umit Cali

Quantum machine learning (QML) is a promising paradigm for tackling computational problems that challenge classical AI. Yet, the inherent probabilistic behavior of quantum mechanics, device noise in NISQ hardware, and hybrid quantum-classical execution pipelines introduce new risks that prevent reliable deployment of QML in real-world, safety-critical settings. This research offers a broad roadmap for Trustworthy Quantum Machine Learning (TQML), integrating three foundational pillars of reliability: (i) uncertainty quantification for calibrated and risk-aware decision making, (ii) adversarial robustness against classical and quantum-native threat models, and (iii) privacy preservation in distributed and delegated quantum learning scenarios. We formalize quantum-specific trust metrics grounded in quantum information theory, including a variance-based decomposition of predictive uncertainty, trace-distance-bounded robustness, and differential privacy for hybrid learning channels. To demonstrate feasibility on current NISQ devices, we validate a unified trust assessment pipeline on parameterized quantum classifiers, uncovering correlations between uncertainty and prediction risk, an asymmetry in attack vulnerability between classical and quantum state perturbations, and privacy-utility trade-offs driven by shot noise and quantum channel noise. This roadmap seeks to define trustworthiness as a first-class design objective for quantum AI.

quant-pharXiv:2511.02602•Nov 5, 2025•7 citations

VeriQR: A Robustness Verification Tool for Quantum Machine Learning Models

Yanling Lin, Ji Guan, Fang Wang +2 more

Adversarial noise attacks present a significant threat to quantum machine learning (QML) models, similar to their classical counterparts. This is especially true in the current Noisy Intermediate-Scale Quantum era, where noise is unavoidable. Therefore, it is essential to ensure the robustness of QML models before their deployment. To address this challenge, we introduce \textit{VeriQR}, the first tool designed specifically for formally verifying and improving the robustness of QML models, to the best of our knowledge. This tool mimics real-world quantum hardware's noisy impacts by incorporating random noise to formally validate a QML model's robustness. \textit{VeriQR} supports exact (sound and complete) algorithms for both local and global robustness verification. For enhanced efficiency, it implements an under-approximate (complete) algorithm and a tensor network-based algorithm to verify local and global robustness, respectively. As a formal verification tool, \textit{VeriQR} can detect adversarial examples and utilize them for further analysis and to enhance the local robustness through adversarial training, as demonstrated by experiments on real-world quantum machine learning models. Moreover, it permits users to incorporate customized noise. Based on this feature, we assess \textit{VeriQR} using various real-world examples, and experimental outcomes confirm that the addition of specific quantum noise can enhance the global robustness of QML models. These processes are made accessible through a user-friendly graphical interface provided by \textit{VeriQR}, catering to general users without requiring a deep understanding of the counter-intuitive probabilistic nature of quantum computing.

arXiv:2407.13533•Jul 18, 2024•8 citations

Quantum Machine Learning for Noisy Intermediate-Scale Quantum Devices: A Comprehensive Review

Quantum computing has emerged as a transformative paradigm capable of addressing computational challenges beyond the reach of classical systems.In the current era of Noisy Intermediate-Scale Quantum (NISQ) devices, practical quantum hardware is characterized by limited qubit counts, short coherence times, gate errors, and the absence of full error correction.Despite these constraints, significant progress has been made in developing quantum machine learning (QML) techniques tailored to operate on near-term quantum processors.This paper presents a comprehensive review of Quantum Machine Learning in the context of NISQ computing.We first outline the fundamental principles of quantum computing, including qubits, superposition, entanglement, and quantum parallelism, followed by a detailed discussion of the NISQ computing model and its hardware limitations.The review then examines hybrid quantum-classical learning frameworks, variational quantum algorithms, quantum data encoding strategies, and noise mitigation techniques that enable practical implementation on existing platforms.Emerging applications across healthcare, finance, cybersecurity, climate modeling, and materials science are also surveyed to highlight the real-world potential of QML.Furthermore, key challenges such as scalability, trainability issues, and algorithmic robustness are analyzed, along with current research efforts aimed at overcoming these barriers.The paper concludes by identifying promising future directions for advancing QML toward quantum advantage.This review aims to provide researchers and practitioners with a structured understanding of the capabilities, limitations, and opportunities of quantum machine learning in the NISQ era .

International Research Journal of Modernization in Engineering Technology and Science•Apr 9, 2026•0 citations
Quantum machine learning (QML) is an emerging paradigm that aims to achieve high expressive power by leveraging quantum advantage. However, realizing these advantages in practice inevitably requires executing inference on remote, noisy quantum hardware. Such hardware produces probabilistic and non-reproducible outcomes, leaving classical users without a principled way to verify reported results. We proposezkQML, the first framework that enables a fully classical verifier to certify that a reported QML inference result is consistent with a committed model up to a device-calibrated noise tolerance, by leveraging zero-knowledge succinct non-interactive argument of knowledge (zk-SNARKs). zkQML arithmetizes the ideal semantics of quantum inference and enforces consistency using cryptographic zk-SNARKs, while explicitly accounting for device noise through a noise-bounded correctness notion. Experiments on both simulators and real quantum hardware show that the proposed arithmetic modeling closely matches ideal quantum inference and enables verifier-efficient verification with small proof sizes and near-constant verification time. These results demonstrate that zkQML provides a practical and sound foundation for trustworthy quantum inference in realistic, non-reproducible execution environments.
Quantum machine learning (QML) has attracted growing interest for their ability to achieve superior performance with significantly fewer parameters. However, the high cost and scarcity of current hardware push inference to cloud-hosted quantum devices, creating a tension between verifiability and confidentiality. This work proposes a novel framework that converts quantum neural network operations into classical arithmetic circuits that faithfully approximate genuine quantum computations. By encrypting these circuits with zero-knowledge proofs, it ensures computational validity while concealing internal parameters. Experimental results show that our classical circuits achieve fidelity above 0.9996 and total variation distance below 1% compared to actual quantum computations, verifying the practicality of trustworthy and privacy-preserving quantum inference.
As with classical neural networks, quantum machine learning (QML) models are vulnerable to small input perturbations that can significantly alter output predictions. Certifying the robustness of QML models, particularly on NISQ hardware, is therefore a fundamental step toward trustworthy quantum AI. This chapter reviews our recently developed comprehensive formal framework for verifying adversarial robustness in QML. The core of this framework is a fidelity-based robustness lower bound computable directly from the measurement outcome distribution, which enables both formal verification and empirical estimation on real quantum devices. Additionally, the optimal bound can be computed via semidefinite programming (SDP) with full knowledge of the quantum machine learning models. We incorporate these results into: (1) an efficient formal verification framework; (2) VeriQR, the first dedicated QML robustness verification tool; and (3) the first experimental benchmark of quantum adversarial robustness on a 20-qubit superconducting processor. Together, these systematic advances enable scalable, physically grounded robustness evaluation of QML models.
Abstract Adversarial noise attacks present a significant threat to quantum machine learning (QML) models, similar to their classical counterparts. This is especially true in the current Noisy Intermediate-Scale Quantum era, where noise is unavoidable. Therefore, it is essential to ensure the robustness of QML models before their deployment. To address this challenge, we introduce VeriQR, the first tool designed specifically for formally verifying and improving the robustness of QML models, to the best of our knowledge. This tool mimics real-world quantum hardware’s noisy impacts by incorporating random noise to formally validate a QML model’s robustness. VeriQR supports exact (sound and complete) algorithms for both local and global robustness verification. For enhanced efficiency, it implements an under-approximate (complete) algorithm and a tensor network-based algorithm to verify local and global robustness, respectively. As a formal verification tool, VeriQR can detect adversarial examples and utilize them for further analysis and to enhance the local robustness through adversarial training, as demonstrated by experiments on real-world quantum machine learning models. Moreover, it permits users to incorporate customized noise. Based on this feature, we assess VeriQR using various real-world examples, and experimental outcomes confirm that the addition of specific quantum noise can enhance the global robustness of QML models. These processes are made accessible through a user-friendly graphical interface provided by VeriQR, catering to general users without requiring a deep understanding of the counter-intuitive probabilistic nature of quantum computing.
Quantum machine learning (QML) is a promising paradigm for tackling computational problems that challenge classical AI. Yet, the inherent probabilistic behavior of quantum mechanics, device noise in NISQ hardware, and hybrid quantum-classical execution pipelines introduce new risks that prevent reliable deployment of QML in real-world, safety-critical settings. This research offers a broad roadmap for Trustworthy Quantum Machine Learning (TQML), integrating three foundational pillars of reliability: (i) uncertainty quantification for calibrated and risk-aware decision making, (ii) adversarial robustness against classical and quantum-native threat models, and (iii) privacy preservation in distributed and delegated quantum learning scenarios. We formalize quantum-specific trust metrics grounded in quantum information theory, including a variance-based decomposition of predictive uncertainty, trace-distance-bounded robustness, and differential privacy for hybrid learning channels. To demonstrate feasibility on current NISQ devices, we validate a unified trust assessment pipeline on parameterized quantum classifiers, uncovering correlations between uncertainty and prediction risk, an asymmetry in attack vulnerability between classical and quantum state perturbations, and privacy-utility trade-offs driven by shot noise and quantum channel noise. This roadmap seeks to define trustworthiness as a first-class design objective for quantum AI.
Adversarial noise attacks present a significant threat to quantum machine learning (QML) models, similar to their classical counterparts. This is especially true in the current Noisy Intermediate-Scale Quantum era, where noise is unavoidable. Therefore, it is essential to ensure the robustness of QML models before their deployment. To address this challenge, we introduce \textit{VeriQR}, the first tool designed specifically for formally verifying and improving the robustness of QML models, to the best of our knowledge. This tool mimics real-world quantum hardware's noisy impacts by incorporating random noise to formally validate a QML model's robustness. \textit{VeriQR} supports exact (sound and complete) algorithms for both local and global robustness verification. For enhanced efficiency, it implements an under-approximate (complete) algorithm and a tensor network-based algorithm to verify local and global robustness, respectively. As a formal verification tool, \textit{VeriQR} can detect adversarial examples and utilize them for further analysis and to enhance the local robustness through adversarial training, as demonstrated by experiments on real-world quantum machine learning models. Moreover, it permits users to incorporate customized noise. Based on this feature, we assess \textit{VeriQR} using various real-world examples, and experimental outcomes confirm that the addition of specific quantum noise can enhance the global robustness of QML models. These processes are made accessible through a user-friendly graphical interface provided by \textit{VeriQR}, catering to general users without requiring a deep understanding of the counter-intuitive probabilistic nature of quantum computing.
Quantum computing has emerged as a transformative paradigm capable of addressing computational challenges beyond the reach of classical systems.In the current era of Noisy Intermediate-Scale Quantum (NISQ) devices, practical quantum hardware is characterized by limited qubit counts, short coherence times, gate errors, and the absence of full error correction.Despite these constraints, significant progress has been made in developing quantum machine learning (QML) techniques tailored to operate on near-term quantum processors.This paper presents a comprehensive review of Quantum Machine Learning in the context of NISQ computing.We first outline the fundamental principles of quantum computing, including qubits, superposition, entanglement, and quantum parallelism, followed by a detailed discussion of the NISQ computing model and its hardware limitations.The review then examines hybrid quantum-classical learning frameworks, variational quantum algorithms, quantum data encoding strategies, and noise mitigation techniques that enable practical implementation on existing platforms.Emerging applications across healthcare, finance, cybersecurity, climate modeling, and materials science are also surveyed to highlight the real-world potential of QML.Furthermore, key challenges such as scalability, trainability issues, and algorithmic robustness are analyzed, along with current research efforts aimed at overcoming these barriers.The paper concludes by identifying promising future directions for advancing QML toward quantum advantage.This review aims to provide researchers and practitioners with a structured understanding of the capabilities, limitations, and opportunities of quantum machine learning in the NISQ era .