Work

Quantum Neural Network Extraction Attack via Split Co-Teaching

Year: 2025

Type: conference-paper

Abstract: Quantum Neural Networks (QNNs), now offered as QNN-as-a-Service (QNNaaS), have become key targets for model extraction attacks. Existing methods use ensemble learning to train substitute QNNs, but our analysis reveals significant limitations in real-world environments, where noise and cost constraints undermine their effectiveness. In this work, we introduce a novel attack, split co-teaching, which uses label variations to split queried data by noise sensitivity and employs co-teaching schemes to enhance extraction accuracy. The experimental results show that our approach outperforms classical extraction attacks by 6.5%~9.5% and existing QNN extraction methods by 0.1%~3.7% across various tasks.

Source: IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)

DOI: 10.1109/icasspw65056.2025.11011056

Authors: Zhenxiao Fu, Fan Chen

Institutions: Indiana University Bloomington, Indiana University

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Awards: CAREER: System Support for Scalable, Fast, and Power-Efficient Genome Sequencing, CyberTraining: Implementation: Small: Establishing Advanced and Secure Quantum Cyberinfrastructure through Curriculum Development and Workforce Training