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

Proceedings of the AAAI Conference on Artificial Intelligence

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

Seung Kwon Lee, Seok Bin Son, Joongheon Kim, Hoh Peter In

Published Mar 14, 2026• 3 citations
Publisher

Abstract

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.

DOI
10.1609/aaai.v40i48.42232

Related papers

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

Seungkwon Lee, Seok Bin Son, Chaeyeon Kim +2 more

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.

IEEE Internet of Things Journal•Aug 31, 2026•0 citations

Quantum machine learning with differential privacy

William M. Watkins, Samuel Yen-Chi Chen, Shinjae Yoo

Quantum machine learning (QML) can complement the growing trend of using learned models for a myriad of classification tasks, from image recognition to natural speech processing. There exists the potential for a quantum advantage due to the intractability of quantum operations on a classical computer. Many datasets used in machine learning are crowd sourced or contain some private information, but to the best of our knowledge, no current QML models are equipped with privacy-preserving features. This raises concerns as it is paramount that models do not expose sensitive information. Thus, privacy-preserving algorithms need to be implemented with QML. One solution is to make the machine learning algorithm differentially private, meaning the effect of a single data point on the training dataset is minimized. Differentially private machine learning models have been investigated, but differential privacy has not been thoroughly studied in the context of QML. In this study, we develop a hybrid quantum-classical model that is trained to preserve privacy using differentially private optimization algorithm. This marks the first proof-of-principle demonstration of privacy-preserving QML. The experiments demonstrate that differentially private QML can protect user-sensitive information without signficiantly diminishing model accuracy. Although the quantum model is simulated and tested on a classical computer, it demonstrates potential to be efficiently implemented on near-term quantum devices [noisy intermediate-scale quantum (NISQ)]. The approach's success is illustrated via the classification of spatially classed two-dimensional datasets and a binary MNIST classification. This implementation of privacy-preserving QML will ensure confidentiality and accurate learning on NISQ technology.

arXiv:2103.06232•Scientific Reports•Feb 11, 2023•93 citations

Hybrid Quantum-Classical Computing for Privacy-Preserving Machine Learning on Edge Devices

B. Dinesh, M. Thangamani, B. Paulchamy +3 more

The edge computing environment faces a challenge in maintaining data privacy while performing machine learning tasks. The current solutions for privacy preservation are inefficient or do not provide security guarantees, causing a critical gap in the edge computing environment, which is resource-constrained. The aim of this research work is to design a hybrid quantum-classical computing system that addresses the challenges of privacy preservation and efficiency in machine learning tasks. We design a novel architecture combining variational quantum circuits for secure data encoding with classical neural networks for scalable inference, implemented through federated learning protocols enhanced with quantum differential privacy mechanisms. Experimental evaluation demonstrates a 35% reduction in communication overhead compared to traditional federated learning approaches while maintaining 99.2% classification accuracy across diverse datasets. The quantum-enhanced privacy mechanisms achieve provable security guarantees with information-theoretic bounds, outperforming conventional cryptographic methods by 28% in computational overhead reduction. This hybrid approach establishes a new paradigm for secure and efficient machine learning deployment on edge devices, enabling privacy-preserving artificial intelligence in healthcare, finance, and IoT applications.

IEEE International Conference on Emerging Computing and Intelligent Technologies (ICoECIT)•Jan 28, 2026•0 citations

Quantum Circuit-Based Learning Models: Bridging Quantum Computing and Machine Learning

Fan Fan, Yilei Shi, Mihai Datcu +5 more

Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges. Quantum Computing (QC), which exploits quantum mechanisms for computation, has attracted growing attention and significant global investment as it may address these challenges. Consequently, Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.

quant-pharXiv:2602.00048•Artificial Intelligence Review•Jan 20, 2026•2 citations

Quantum Quandaries: Unraveling Encoding Vulnerabilities in Quantum Neural Networks

Suryansh Upadhyay, Swaroop Ghosh

Quantum computing (QC) has the potential to revolutionize fields like machine learning, security, and healthcare. Quantum machine learning (QML) has emerged as a promising area, enhancing learning algorithms using quantum computers. However, QML models are lucrative targets due to their high training costs and extensive training times. The scarcity of quantum resources and long wait times further exacerbate the challenge. Additionally, QML providers may rely on third-party quantum clouds for hosting models, exposing them and their training data to potential threats. As QML-as-a-Service (QMLaaS) becomes more prevalent, reliance on third-party quantum clouds poses a significant security risk. This work demonstrates that adversaries in quantum cloud environments can exploit white-box access to QML models to infer the user's encoding scheme by analyzing circuit transpilation artifacts. The extracted data can be reused for training clone models or sold for profit. We validate the proposed attack through simulations, achieving high accuracy in distinguishing between encoding schemes. We report that ≈95% of the time, the encoding can be predicted correctly. To mitigate this threat, we propose a transient obfuscation layer that masks encoding fingerprints using randomized rotations and entanglement, reducing adversarial detection to near-random chance ≈42%, with a depth overhead of ≈8.5% for a 5-layer QNN design.

arXiv:2502.01486•International Symposium on Quality Electronic Design (ISQED)•Apr 23, 2025•8 citations

Reverse Delegated Training and Private Inference via Perfectly-Secure Quantum Homomorphic Encryption

Sergio A. Ortega, Miguel A. Martin-Delgado

Quantum machine learning in cloud environments requires protecting sensitive data while enabling remote computation. Here we demonstrate the first realistic implementations of a perfectly-secure quantum homomorphic encryption (QHE) scheme applied to quantum neural networks (QNN). Using efficient Clifford+$T$ decomposition, we implement quantum convolutional neural networks for two complementary scenarios: (i) reverse delegated training, where encrypted data from multiple providers trains a user's network via federated aggregation; (ii) private inference, where users process encrypted data with remote quantum networks. Moreover, analysis of server circuit privacy reveals probabilistic model protection through Pauli gate concealment. These results establish perfectly-secure QHE as a practical framework for multi-party quantum machine learning.

quant-pharXiv:2602.12712•Feb 16, 2026•0 citations
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.
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) can complement the growing trend of using learned models for a myriad of classification tasks, from image recognition to natural speech processing. There exists the potential for a quantum advantage due to the intractability of quantum operations on a classical computer. Many datasets used in machine learning are crowd sourced or contain some private information, but to the best of our knowledge, no current QML models are equipped with privacy-preserving features. This raises concerns as it is paramount that models do not expose sensitive information. Thus, privacy-preserving algorithms need to be implemented with QML. One solution is to make the machine learning algorithm differentially private, meaning the effect of a single data point on the training dataset is minimized. Differentially private machine learning models have been investigated, but differential privacy has not been thoroughly studied in the context of QML. In this study, we develop a hybrid quantum-classical model that is trained to preserve privacy using differentially private optimization algorithm. This marks the first proof-of-principle demonstration of privacy-preserving QML. The experiments demonstrate that differentially private QML can protect user-sensitive information without signficiantly diminishing model accuracy. Although the quantum model is simulated and tested on a classical computer, it demonstrates potential to be efficiently implemented on near-term quantum devices [noisy intermediate-scale quantum (NISQ)]. The approach's success is illustrated via the classification of spatially classed two-dimensional datasets and a binary MNIST classification. This implementation of privacy-preserving QML will ensure confidentiality and accurate learning on NISQ technology.
The edge computing environment faces a challenge in maintaining data privacy while performing machine learning tasks. The current solutions for privacy preservation are inefficient or do not provide security guarantees, causing a critical gap in the edge computing environment, which is resource-constrained. The aim of this research work is to design a hybrid quantum-classical computing system that addresses the challenges of privacy preservation and efficiency in machine learning tasks. We design a novel architecture combining variational quantum circuits for secure data encoding with classical neural networks for scalable inference, implemented through federated learning protocols enhanced with quantum differential privacy mechanisms. Experimental evaluation demonstrates a 35% reduction in communication overhead compared to traditional federated learning approaches while maintaining 99.2% classification accuracy across diverse datasets. The quantum-enhanced privacy mechanisms achieve provable security guarantees with information-theoretic bounds, outperforming conventional cryptographic methods by 28% in computational overhead reduction. This hybrid approach establishes a new paradigm for secure and efficient machine learning deployment on edge devices, enabling privacy-preserving artificial intelligence in healthcare, finance, and IoT applications.
Machine Learning (ML) has been widely applied across numerous domains due to its ability to automatically identify informative patterns from data for various tasks. The availability of large-scale data and advanced computational power enables the development of sophisticated models and training strategies, leading to state-of-the-art performance, but it also introduces substantial challenges. Quantum Computing (QC), which exploits quantum mechanisms for computation, has attracted growing attention and significant global investment as it may address these challenges. Consequently, Quantum Machine Learning (QML), the integration of these two fields, has received increasing interest, with a notable rise in related studies in recent years. We are motivated to review these existing contributions regarding quantum circuit-based learning models for classical data analysis and highlight the identified potentials and challenges of this technique. Specifically, we focus not only on QML models, both kernel-based and neural network-based, but also on recent explorations of their integration with classical machine learning layers within hybrid frameworks. Moreover, we examine both theoretical analysis and empirical findings to better understand their capabilities, and we also discuss the efforts on noise-resilient and hardware-efficient QML that could enhance its practicality under current hardware limitations. In addition, we cover several emerging paradigms for advanced quantum circuit design and highlight the adaptability of QML across representative application domains. This study aims to provide an overview of the contributions made to bridge quantum computing and machine learning, offering insights and guidance to support its future development and pave the way for broader adoption in the coming years.
Quantum computing (QC) has the potential to revolutionize fields like machine learning, security, and healthcare. Quantum machine learning (QML) has emerged as a promising area, enhancing learning algorithms using quantum computers. However, QML models are lucrative targets due to their high training costs and extensive training times. The scarcity of quantum resources and long wait times further exacerbate the challenge. Additionally, QML providers may rely on third-party quantum clouds for hosting models, exposing them and their training data to potential threats. As QML-as-a-Service (QMLaaS) becomes more prevalent, reliance on third-party quantum clouds poses a significant security risk. This work demonstrates that adversaries in quantum cloud environments can exploit white-box access to QML models to infer the user's encoding scheme by analyzing circuit transpilation artifacts. The extracted data can be reused for training clone models or sold for profit. We validate the proposed attack through simulations, achieving high accuracy in distinguishing between encoding schemes. We report that ≈95% of the time, the encoding can be predicted correctly. To mitigate this threat, we propose a transient obfuscation layer that masks encoding fingerprints using randomized rotations and entanglement, reducing adversarial detection to near-random chance ≈42%, with a depth overhead of ≈8.5% for a 5-layer QNN design.
Quantum machine learning in cloud environments requires protecting sensitive data while enabling remote computation. Here we demonstrate the first realistic implementations of a perfectly-secure quantum homomorphic encryption (QHE) scheme applied to quantum neural networks (QNN). Using efficient Clifford+TTT decomposition, we implement quantum convolutional neural networks for two complementary scenarios: (i) reverse delegated training, where encrypted data from multiple providers trains a user's network via federated aggregation; (ii) private inference, where users process encrypted data with remote quantum networks. Moreover, analysis of server circuit privacy reveals probabilistic model protection through Pauli gate concealment. These results establish perfectly-secure QHE as a practical framework for multi-party quantum machine learning.