通过梯度反演恢复量子神经网络训练数据，挑战了其安全性。
A Numerical Gradient Inversion Attack in Variational Quantum Neural-Networks
- 结合有限差分与自适应低通滤波实现梯度反演。
- 在过参数化模型下可逆演出批量训练数据。
- 适用于研究量子模型隐私风险的科研人员。
变分量子神经网络（VQNNs）的损失曲面随量子比特数增加呈现指数级增长的局部极小值，导致训练过程中从模型梯度中恢复信息比经典神经网络更困难。本文提出一种数值方法，成功从可训练的VQNN梯度中重构出输入训练数据，包括真实世界实际数据。该方法基于梯度反演，结合梯度估计与有限差分法，并引入自适应低通滤波。进一步通过卡尔曼滤波优化以实现高效收敛。实验表明，当VQNN模型足够过参数化时，该算法能有效逆演出批量训练数据。
原文摘要 · Abstract (English)
The loss landscape of Variational Quantum Neural Networks (VQNNs) is characterized by local minima that grow exponentially with increasing qubits. Because of this, it is more challenging to recover information from model gradients during training compared to classical Neural Networks (NNs). In this paper we present a numerical scheme that successfully reconstructs input training, real-world, practical data from trainable VQNNs' gradients. Our scheme is based on gradient inversion that works by combining gradients estimation with the finite difference method and adaptive low-pass filtering. The scheme is further optimized with Kalman filter to obtain efficient convergence. Our experiments show that our algorithm can invert even batch-trained data, given the VQNN model is sufficiently over-parameterized.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。