QUFIG: GNN-Based Prediction of Quantum Fault Injection Vulnerabilities with Gate-Level Precision
Abstract
The growing scale and accessibility of quantum hardware exposed new reliability and security challenges in the quantum computing workflow, such as the run-time fault injection attacks in cloud-based quantum computing platforms. However, existing works fail to identify vulnerabilities with gate-level precision or adapt to run-time environments. In this work, we formulate gate-level fault analysis as a learning-guided prioritization problem under restricted fidelity budgets. The framework uses a circuit-DAG-based GNN backbone to predict the vulnerability score of each gate to each type of injected fault, defined as the impact of the gate-fault pair on circuit fidelity. The gate-fault pairs are then ranked by their vulnerability score. Experiments on QASMbench and HamLib MaxCut show that QUFIG recovers high-impact vulnerable gate-fault pairs with fewer inspections than random and depth-based heuristics. Our results show that QUFIG can reduce the number of gates requiring inspection by 2.9--19.8% while maintaining effective fault identification, allowing quantum circuit designers to identify vulnerabilities and apply targeted defenses more efficiently.
Related
- ANN-based prediction of torsional fatigue behavior in an injection-molded compliant mechanism component
- Towards minimal conditions for ergotropy injection in open quantum systems
- A Hybrid Quantum-Classical Coordination Architecture for Portfolio Optimization via Global Context Injection
- Constant-Overhead Injection into Quantum Codes
- Efficient Quantum Simulation of Variable-Coefficient Transport with Continuous Source Injection
BibTeX
@misc{zhao2026qufig,
title = {{QUFIG: GNN-Based Prediction of Quantum Fault Injection Vulnerabilities with Gate-Level Precision}},
author = {Shihan Zhao and Qiying Li and Ben Dong and Qian Wang and Yuntao Liu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.01777},
eprint = {2610.01777},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.01777},
}
RIS
TY - UNPB
TI - QUFIG: GNN-Based Prediction of Quantum Fault Injection Vulnerabilities with Gate-Level Precision
AU - Shihan Zhao
AU - Qiying Li
AU - Ben Dong
AU - Qian Wang
AU - Yuntao Liu
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.01777
UR - https://arxiv.org/abs/2610.01777
AB - The growing scale and accessibility of quantum hardware exposed new reliability and security challenges in the quantum computing workflow, such as the run-time fault injection attacks in cloud-based quantum computing platforms. However, existing works fail to identify vulnerabilities with gate-level precision or adapt to run-time environments. In this work, we formulate gate-level fault analysis as a learning-guided prioritization problem under restricted fidelity budgets. The framework uses a circuit-DAG-based GNN backbone to predict the vulnerability score of each gate to each type of injected fault, defined as the impact of the gate-fault pair on circuit fidelity. The gate-fault pairs are then ranked by their vulnerability score. Experiments on QASMbench and HamLib MaxCut show that QUFIG recovers high-impact vulnerable gate-fault pairs with fewer inspections than random and depth-based heuristics. Our results show that QUFIG can reduce the number of gates requiring inspection by 2.9--19.8% while maintaining effective fault identification, allowing quantum circuit designers to identify vulnerabilities and apply targeted defenses more efficiently.
ER -