# Fast Fourier Transform-Based Spectral and Temporal Gradient Filtering for Differential Privacy Source: [Fast Fourier Transform-Based Spectral and Temporal Gradient Filtering for Differential Privacy]() Collection index: [llms.txt]() Data updated: 2025-10-25T18:40:59.491Z Authors: Hyeju Shin, Vincent-Daniel, Kyudan Jung, Seongwon Yun Published: 2025-05-07T14:38:58.000Z ## Abstract Differential Privacy (DP) has emerged as a key framework for protecting sensitive data in machine learning, but standard DP-SGD often suffers from significant accuracy loss due to injected noise. To address this limitation, we introduce the FFT-Enhanced Kalman Filter (FFTKF), a differentially private optimization method that improves gradient quality while preserving $(\\varepsilon, \\delta)$-DP guarantees. FFTKF applies frequency-domain filtering to shift privacy noise into less informative high-frequency components, preserving the low-frequency gradient signals that carry most learning information. A scalar-gain Kalman filter with a finite-difference Hessian approximation further refines the denoised gradients. The method has per-iteration complexity $\\mathcal{O}(d \\log d)$ and achieves higher test accuracy than DP-SGD and DiSK on MNIST, CIFAR-10, CIFAR-100, and Tiny-ImageNet with CNNs, Wide ResNets, and Vision Transformers. Theoretical analysis shows that FFTKF ensures equivalent privacy while delivering a stronger privacy--utility trade-off through reduced variance and controlled bias. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()