通过分离协同教学实施的量子神经网络提取攻击
Quantum Neural Network Extraction Attack via Split Co-Teaching
AI总结：
针对 QNNaaS 在噪声与成本受限环境下的模型窃取风险，提出 split co-teaching 攻击，通过按噪声敏感性分离查询数据并协同训练替代 QNN，在多任务上提升提取准确率。
摘要：
量子神经网络（QNNs）如今以 QNN-as-a-Service（QNNaaS）形式提供，已成为模型提取攻击的关键目标。现有方法采用集成学习训练替代 QNN，但我们的分析揭示了其在真实环境中的显著局限：噪声和成本约束会削弱其有效性。本工作提出一种名为 split co-teaching（分离协同教学）的新型攻击，利用标签变化按噪声敏感性分离查询数据，并采用 co-teaching 机制提升提取准确率。实验结果表明，在多种任务上，该方法比经典提取攻击高 6.5%~9.5%，比现有 QNN 提取方法高 0.1%~3.7%。
英文摘要：
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, \textit{split co-teaching}, which uses label variations to \textit{split} queried data by noise sensitivity and employs \textit{co-teaching} schemes to enhance extraction accuracy. The experimental results show that our approach outperforms classical extraction attacks by 6.5\%$\sim$9.5\% and existing QNN extraction methods by 0.1\%$\sim$3.7\% across various tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
