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:2512.14541

A Graph-Based Forensic Framework for Inferring Hardware Noise of Cloud Quantum Backend

Subrata Das, Archisman Ghosh, Swaroop Ghosh

quant-phcs.ETSubmitted Dec 16, 2025• Announced Dec 17, 2025• 0 citations
arXivHTMLPDF

Abstract

Cloud quantum platforms give users access to many backends with different qubit technologies, coupling layouts, and noise levels. The execution of a circuit, however, depends on internal allocation and routing policies that are not observable to the user. A provider may redirect jobs to more error-prone regions to conserve resources, balance load or for other opaque reasons, causing degradation in fidelity while still presenting stale or averaged calibration data. This lack of transparency creates a security gap: users cannot verify whether their circuits were executed on the hardware for which they were charged. Forensic methods that infer backend behavior from user-visible artifacts are therefore becoming essential. In this work, we introduce a Graph Neural Network (GNN)-based forensic framework that predicts per-qubit and per-qubit link error rates of an unseen backend using only topology information and aggregated features extracted from transpiled circuits. We construct a dataset from several IBM 27-qubit devices, merge static calibration features with dynamic transpilation features and train separate GNN regressors for one- and two-qubit errors. At inference time, the model operates without access to calibration data from the target backend and reconstructs a complete error map from the features available to the user. Our results on the target backend show accurate recovery of backend error rate, with an average mismatch of approximately 22% for single-qubit errors and 18% for qubit-link errors. The model also exhibits strong ranking agreement, with the ordering induced by predicted error values closely matching that of the actual calibration errors, as reflected by high Spearman correlation. The framework consistently identifies weak links and high-noise qubits and remains robust under realistic temporal noise drift.

Comments
11 pages, 5 figures, conference

Related papers

Forensics of Error Rates of Quantum Hardware

Rupshali Roy, Swaroop Ghosh

The qubit technologies, basis gate set, noise behavior, speed and coupling architecture are among the various factors that vary among various backends. Although third-party cloud providers offering quantum hardware as a service offer lower cost and flexibility to the users to choose from several qubit technologies, quantum hardware, and coupling maps; the actual execution of the program is not clearly visible to the customer. The success of the user program, in addition to various other metadata such as cost, performance, & number of iterations to converge, depends on the error rate of the backend used. Moreover, the third-party provider and/or tools (e.g., hardware allocator and mapper) may hold insider/outsider adversarial agents to conserve resources and maximize profit by running the quantum circuits on error-prone hardware. Thus it is important to gain visibility of the backend from various perspectives of the computing process e.g., execution, transpilation and outcomes. In this paper, we estimate the error rate of the backend from the original and transpiled circuit. Although many quantum services providers publish the error rates of their backends, we assume that such information may not be accurate and/or correspond to the actual hardware allocated to the program. For the forensics we propose two complementary approaches. First, we exploit the fact that qubit mapping and routing steps of the transpilation process select qubits and qubit pairs with low gate errors to minimize overall error accumulation. We leverage this to rank qubit links into bins and compare with publicly available data we are able to assign a bin rank within a difference of 2 with respect to the actual bin for upto$\mathbf{8 3. 5 \%}$of the qubit links in IBM Sherbrooke and$\mathbf{8 0 \%}$in IBM Brisbane, 127 qubit IBM backends. Second, we derive the error rates of the backends from a pool of programs by solving fidelity equations using numerical nonlinear optimizer. We achieve upto$92.7 \%(97.3 \%)$accuracy for single qubit (2 qubit) gate error rates.

arXiv:2505.11706•IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD)•Nov 10, 2025•1 citation

Forensics of Transpiled Quantum Circuits

Rupshali Roy, Archisman Ghosh, Swaroop Ghosh

Many third-party cloud providers set up quantum hardware as a service that includes a wide range of qubit technologies and architectures to maximize performance at minimal cost. However, there is little visibility to where the execution of the circuit is taking place. This situation is similar to the classical cloud. The difference in the quantum scenario is that the success of the user program is highly reliant on the backend used. Besides, the third-party provider may be untrustworthy and execute the quantum circuits on less efficient and more error-prone hardware to maximize profit. Thus, gaining visibility on the backend from various aspects will be valuable. Effective forensics can have many applications including establishing trust in quantum cloud services. We introduce the problem of forensics in the domain of quantum computing. We trace the coupling map of the hardware where the transpilation of the circuit took place from the transpiled program. We perform experiments on various coupling topologies (linear, T-shaped, H-shaped, and loop) on IBM backends. We can derive the coupling map from the transpiled circuits with complete accuracy for almost every transpiled circuit we considered. We could correctly trace 97.33% of the programs to the correct backend.

arXiv:2412.18939•ACM Great Lakes Symposium on VLSI (GLSVLSI)•Jun 27, 2025•5 citations

Program Queue Analysis for Forensics of Quantum Backends

Rupshali Roy, Swaroop Ghosh

Third-party cloud providers offer quantum hardware as a service enabling flexibility to the customers to opt from varied quantum hardware, qubit technologies and topologies. However, the actual execution of the program on the desired target hardware remains opaque to the user. On one hand, the program performance, along with various other metadata such as cost, performance, & number of iterations to converge, is dependent on the quality of the backend chosen. on the other hand, the third-party provider and/or tools (e.g., hardware schedulers) may maximize profit by running the quantum circuits on poor quality backend while charging for the high quality backend. Existing approaches to mitigate this opaqueness rely on forensics of error rates and coupling topology from transpiled circuit. We note that program queue depth and execution time are well correlated with the backend and therefore, can reveal vital information about the hardware and aid in forensic analysis to address the opaqueness.

IEEE Dallas Circuits and Systems Conference (DCAS)•Apr 10, 2026•0 citations

Transpilation-Aware Runtime Prediction for Noisy Quantum Circuit Simulation

Davud Azizov, Javier Vela-Tambo, Tian Guo

Predicting the runtime of noisy quantum circuit simulations is important for scheduling, resource allocation, and performance optimization. However, accurate prediction is challenging because backend-aware transpilation can substantially alter the original circuit structure, while the backend-derived noise model and simulator execution behavior can introduce additional runtime variation. We study the effectiveness of graph neural networks (GNNs) and conventional regression methods in predicting Qiskit Aer simulation runtime measured after transpilation. We construct a dataset from a benchmark pool of 1,402 unique circuits spanning 22 circuit families, two Qiskit fake-backend configurations, and four transpiler optimization levels. Specifically, we compare a source GNN using original circuit information, hybrid GNN combining source-level graph with post-transpilation features, and transpiled GNN using only transpiled circuit information, along with five regression models. In the overall-model setting, the transpiled GNN achieves the strongest performance among the graph-based representations at all four optimization levels, obtaining $R^2$ values of 0.974, 0.713, 0.745, and 0.605 for optimization levels 0 through 3, respectively. However, under backend-specific evaluation, the advantage of GNN decreases, with conventional regression models matching or outperforming the GNNs in several settings. These results indicate that post-transpilation information is useful, while the value of explicit graph modeling depends on the backend and optimization level.

quant-pharXiv:2609.12980•Sep 14, 2026•0 citations

Calibration-Aware Graph Neural Networks for Robust and Scalable Quantum Error Mitigation

Zhihao Shen

Abstract Noisy Intermediate-Scale Quantum (NISQ) computing is fundamentally constrained by hardware noise that is not only large but also temporally drifting and structurally complex. Traditional quantum error mitigation (QEM) techniques, such as Zero-Noise Extrapolation (ZNE), often rely on simplified noise assumptions that degrade under coherent errors and deep circuit structures. Conversely, existing machine learning-based QEM approaches typically treat device noise as a static background, leading to poor generalization when hardware calibration shifts. In this work, we propose \textbf{Calib-GNN}, a novel framework that explicitly integrates real-time hardware calibration data into a Graph Neural Network (GNN) architecture. By embedding gate-specific error rates directly into the graph representation, our model learns a dynamic mapping from noisy measurements to ideal expectation values. Through extensive simulations based on real noise profiles from the IBM Quantum \texttt{ibm\_fez} backend, we demonstrate that Calib-GNN significantly outperforms standard baselines. Specifically, it reduces the Root Mean Square Error (RMSE) by approximately 14\% compared to ZNE on random circuits and exhibits superior robustness against severe noise drift where traditional models fail. Furthermore, we show that Calib-GNN effectively scales to deeper circuits and recovers the ground state energy of the $H_2$ molecule in Variational Quantum Eigensolver (VQE) tasks with high fidelity, overcoming the limitations of ZNE in the presence of coherent noise.

•Dec 2, 2025•0 citations

Data-Driven Reliability Models of Quantum Circuit: From Traditional ML to Graph Neural Network

Vedika Saravanan, Samah Mohamed Saeed

The current advancement in quantum computers has been focusing on increasing the number of qubits and enhancing their fidelity. However, the available quantum devices, known as intermediate scale quantum (NISQ) computers, still suffer from different sources of noise that impact their reliability. Thus, practical noise modeling is of great importance in the development of quantum error mitigation approaches. In this article, we propose a machine learning (ML)-based scheme to predict the output fidelity of the quantum circuit executed on NISQ devices. We show the benefit of using graph neural network (GNN)-based models compared to traditional ML-based models in capturing the quantum circuit structure in addition to its gates’ features, which enable characterizing unpredicted quantum circuit errors. We use different metrics to measure the fidelity of the quantum circuit output. Our experimental results using different quantum algorithms executed on IBM Q Guadalupe quantum computer show the high prediction accuracy of our ML reliability models. Our results also show that our models can guide the single-qubit gate rescheduling to improve the output fidelity of the quantum circuit without the need for prior execution of dedicated calibration circuits.

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems•Sep 5, 2022•22 citations
Cloud quantum platforms give users access to many backends with different qubit technologies, coupling layouts, and noise levels. The execution of a circuit, however, depends on internal allocation and routing policies that are not observable to the user. A provider may redirect jobs to more error-prone regions to conserve resources, balance load or for other opaque reasons, causing degradation in fidelity while still presenting stale or averaged calibration data. This lack of transparency creates a security gap: users cannot verify whether their circuits were executed on the hardware for which they were charged. Forensic methods that infer backend behavior from user-visible artifacts are therefore becoming essential. In this work, we introduce a Graph Neural Network (GNN)-based forensic framework that predicts per-qubit and per-qubit link error rates of an unseen backend using only topology information and aggregated features extracted from transpiled circuits. We construct a dataset from several IBM 27-qubit devices, merge static calibration features with dynamic transpilation features and train separate GNN regressors for one- and two-qubit errors. At inference time, the model operates without access to calibration data from the target backend and reconstructs a complete error map from the features available to the user. Our results on the target backend show accurate recovery of backend error rate, with an average mismatch of approximately 22% for single-qubit errors and 18% for qubit-link errors. The model also exhibits strong ranking agreement, with the ordering induced by predicted error values closely matching that of the actual calibration errors, as reflected by high Spearman correlation. The framework consistently identifies weak links and high-noise qubits and remains robust under realistic temporal noise drift.
The qubit technologies, basis gate set, noise behavior, speed and coupling architecture are among the various factors that vary among various backends. Although third-party cloud providers offering quantum hardware as a service offer lower cost and flexibility to the users to choose from several qubit technologies, quantum hardware, and coupling maps; the actual execution of the program is not clearly visible to the customer. The success of the user program, in addition to various other metadata such as cost, performance, & number of iterations to converge, depends on the error rate of the backend used. Moreover, the third-party provider and/or tools (e.g., hardware allocator and mapper) may hold insider/outsider adversarial agents to conserve resources and maximize profit by running the quantum circuits on error-prone hardware. Thus it is important to gain visibility of the backend from various perspectives of the computing process e.g., execution, transpilation and outcomes. In this paper, we estimate the error rate of the backend from the original and transpiled circuit. Although many quantum services providers publish the error rates of their backends, we assume that such information may not be accurate and/or correspond to the actual hardware allocated to the program. For the forensics we propose two complementary approaches. First, we exploit the fact that qubit mapping and routing steps of the transpilation process select qubits and qubit pairs with low gate errors to minimize overall error accumulation. We leverage this to rank qubit links into bins and compare with publicly available data we are able to assign a bin rank within a difference of 2 with respect to the actual bin for upto83.5%\mathbf{8 3. 5 \%}83.5%of the qubit links in IBM Sherbrooke and80%\mathbf{8 0 \%}80%in IBM Brisbane, 127 qubit IBM backends. Second, we derive the error rates of the backends from a pool of programs by solving fidelity equations using numerical nonlinear optimizer. We achieve upto92.7%(97.3%)92.7 \%(97.3 \%)92.7%(97.3%)accuracy for single qubit (2 qubit) gate error rates.
Many third-party cloud providers set up quantum hardware as a service that includes a wide range of qubit technologies and architectures to maximize performance at minimal cost. However, there is little visibility to where the execution of the circuit is taking place. This situation is similar to the classical cloud. The difference in the quantum scenario is that the success of the user program is highly reliant on the backend used. Besides, the third-party provider may be untrustworthy and execute the quantum circuits on less efficient and more error-prone hardware to maximize profit. Thus, gaining visibility on the backend from various aspects will be valuable. Effective forensics can have many applications including establishing trust in quantum cloud services. We introduce the problem of forensics in the domain of quantum computing. We trace the coupling map of the hardware where the transpilation of the circuit took place from the transpiled program. We perform experiments on various coupling topologies (linear, T-shaped, H-shaped, and loop) on IBM backends. We can derive the coupling map from the transpiled circuits with complete accuracy for almost every transpiled circuit we considered. We could correctly trace 97.33% of the programs to the correct backend.
Third-party cloud providers offer quantum hardware as a service enabling flexibility to the customers to opt from varied quantum hardware, qubit technologies and topologies. However, the actual execution of the program on the desired target hardware remains opaque to the user. On one hand, the program performance, along with various other metadata such as cost, performance, & number of iterations to converge, is dependent on the quality of the backend chosen. on the other hand, the third-party provider and/or tools (e.g., hardware schedulers) may maximize profit by running the quantum circuits on poor quality backend while charging for the high quality backend. Existing approaches to mitigate this opaqueness rely on forensics of error rates and coupling topology from transpiled circuit. We note that program queue depth and execution time are well correlated with the backend and therefore, can reveal vital information about the hardware and aid in forensic analysis to address the opaqueness.
Predicting the runtime of noisy quantum circuit simulations is important for scheduling, resource allocation, and performance optimization. However, accurate prediction is challenging because backend-aware transpilation can substantially alter the original circuit structure, while the backend-derived noise model and simulator execution behavior can introduce additional runtime variation. We study the effectiveness of graph neural networks (GNNs) and conventional regression methods in predicting Qiskit Aer simulation runtime measured after transpilation. We construct a dataset from a benchmark pool of 1,402 unique circuits spanning 22 circuit families, two Qiskit fake-backend configurations, and four transpiler optimization levels. Specifically, we compare a source GNN using original circuit information, hybrid GNN combining source-level graph with post-transpilation features, and transpiled GNN using only transpiled circuit information, along with five regression models. In the overall-model setting, the transpiled GNN achieves the strongest performance among the graph-based representations at all four optimization levels, obtaining R2R^2R2 values of 0.974, 0.713, 0.745, and 0.605 for optimization levels 0 through 3, respectively. However, under backend-specific evaluation, the advantage of GNN decreases, with conventional regression models matching or outperforming the GNNs in several settings. These results indicate that post-transpilation information is useful, while the value of explicit graph modeling depends on the backend and optimization level.
Abstract Noisy Intermediate-Scale Quantum (NISQ) computing is fundamentally constrained by hardware noise that is not only large but also temporally drifting and structurally complex. Traditional quantum error mitigation (QEM) techniques, such as Zero-Noise Extrapolation (ZNE), often rely on simplified noise assumptions that degrade under coherent errors and deep circuit structures. Conversely, existing machine learning-based QEM approaches typically treat device noise as a static background, leading to poor generalization when hardware calibration shifts. In this work, we propose \textbf{Calib-GNN}, a novel framework that explicitly integrates real-time hardware calibration data into a Graph Neural Network (GNN) architecture. By embedding gate-specific error rates directly into the graph representation, our model learns a dynamic mapping from noisy measurements to ideal expectation values. Through extensive simulations based on real noise profiles from the IBM Quantum \texttt{ibm\_fez} backend, we demonstrate that Calib-GNN significantly outperforms standard baselines. Specifically, it reduces the Root Mean Square Error (RMSE) by approximately 14\% compared to ZNE on random circuits and exhibits superior robustness against severe noise drift where traditional models fail. Furthermore, we show that Calib-GNN effectively scales to deeper circuits and recovers the ground state energy of the H2H_2H2​ molecule in Variational Quantum Eigensolver (VQE) tasks with high fidelity, overcoming the limitations of ZNE in the presence of coherent noise.
The current advancement in quantum computers has been focusing on increasing the number of qubits and enhancing their fidelity. However, the available quantum devices, known as intermediate scale quantum (NISQ) computers, still suffer from different sources of noise that impact their reliability. Thus, practical noise modeling is of great importance in the development of quantum error mitigation approaches. In this article, we propose a machine learning (ML)-based scheme to predict the output fidelity of the quantum circuit executed on NISQ devices. We show the benefit of using graph neural network (GNN)-based models compared to traditional ML-based models in capturing the quantum circuit structure in addition to its gates’ features, which enable characterizing unpredicted quantum circuit errors. We use different metrics to measure the fidelity of the quantum circuit output. Our experimental results using different quantum algorithms executed on IBM Q Guadalupe quantum computer show the high prediction accuracy of our ML reliability models. Our results also show that our models can guide the single-qubit gate rescheduling to improve the output fidelity of the quantum circuit without the need for prior execution of dedicated calibration circuits.