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

2025-12-16

AI Summary

Cloud quantum platform users cannot verify whether their jobs execute on billed hardware due to opaque backend allocation policies and real-time noise conditions; moreover, calibration data is both outdated and averaged, degrading fidelity and introducing security risks. This paper proposes the first Graph Neural Network (GNN)-based forensic framework tailored for cloud quantum backends. It infers single- and two-qubit error rates solely from the quantum chip’s topology and user-visible compiled circuit features—without requiring real-time calibration data from the target device. The method robustly identifies errors under dynamic noise drift. Experimental evaluation shows mean absolute percentage errors of 22% for single-qubit and 18% for two-qubit error rate predictions, with high Spearman rank correlation. It accurately pinpoints high-noise qubits and low-fidelity coupling links, enabling trustable hardware-level accountability in cloud quantum computing.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Adversarial Attacks & Robustness
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

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.

Problem

• Inferring hardware noise in cloud quantum backends without calibration data
• Predicting per-qubit and qubit-link error rates using topology and circuit features
• Addressing transparency gaps in backend execution and job routing policies

Innovation

• Graph Neural Network predicts qubit error rates
• Uses topology and transpiled circuit features only
• Reconstructs error maps without backend calibration data