# FALCON: A Fourier Transform Based Approach for Fast and Secure Convolutional Neural Network Predictions

arXiv: https://arxiv.org/abs/1811.08257 · HTML: https://mlsanity.com/paper/1811.08257/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2018.

## Built on by (most cited first, 20 of 20)

- [Global Filter Networks for Image Classification](https://mlsanity.com/paper/2107.00645/) (2021)
- [Deep Frequency Filtering for Domain Generalization](https://mlsanity.com/paper/2203.12198/) (2022)
- [Deep Fourier Up-Sampling](https://mlsanity.com/paper/2210.05171/) (2022)
- [Frequency-Aware Masked Autoencoders for Multimodal Pretraining on Biosignals](https://mlsanity.com/paper/2309.05927/) (2023)
- [Frequency Spectrum is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detector](https://mlsanity.com/paper/2312.11023/) (2023)
- [Fast-FNet: Accelerating Transformer Encoder Models via Efficient Fourier Layers](https://mlsanity.com/paper/2209.12816/) (2022)
- [Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations](https://mlsanity.com/paper/2401.05752/) (2024)
- [Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions](https://mlsanity.com/paper/2306.08538/) (2023)
- [Reducing ReLU Count for Privacy-Preserving CNN Speedup](https://mlsanity.com/paper/2101.11835/) (2021)
- [Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation](https://mlsanity.com/paper/2304.10880/) (2023)
- [QFCNN: Quantum Fourier Convolutional Neural Network](https://mlsanity.com/paper/2106.10421/) (2021)
- [Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics](https://mlsanity.com/paper/2408.01701/) (2024)
- [Learning Convolutional Neural Networks in the Frequency Domain](https://mlsanity.com/paper/2204.06718/) (2022)
- [DS-TDNN: Dual-stream Time-delay Neural Network with Global-aware Filter for Speaker Verification](https://mlsanity.com/paper/2303.11020/) (2023)
- [Securing Neural Networks with Knapsack Optimization](https://mlsanity.com/paper/2304.10442/) (2023)
- [FwNet-ECA: A Classification Model Enhancing Window Attention with Global Receptive Fields via Fourier Filtering Operations](https://mlsanity.com/paper/2502.18094/) (2025)
- [MC-MLP:Multiple Coordinate Frames in all-MLP Architecture for Vision](https://mlsanity.com/paper/2304.03917/) (2023)
- [TFDMNet: A Novel Network Structure Combines the Time Domain and Frequency Domain Features](https://mlsanity.com/paper/2401.15949/) (2024)
- [DeepShare: Sharing ReLU Across Channels and Layers for Efficient Private Inference](https://mlsanity.com/paper/2512.17398/) (2025)
- [Deep Psychovisual Image Representations](https://mlsanity.com/paper/2605.29260/) (2026)

## Abstract (arXiv)

Machine learning as a service has been widely deployed to utilize deep neural network models to provide prediction services. However, this raises privacy concerns since clients need to send sensitive information to servers. In this paper, we focus on the scenario where clients want to classify private images with a convolutional neural network model hosted in the server, while both parties keep their data private. We present FALCON, a fast and secure approach for CNN predictions based on Fourier Transform. Our solution enables linear layers of a CNN model to be evaluated simply and efficiently with fully homomorphic encryption. We also introduce the first efficient and privacy-preserving protocol for softmax function, which is an indispensable component in CNNs and has not yet been evaluated in previous works due to its high complexity. We implemented the FALCON and evaluated the performance on real-world CNN models. The experimental results show that FALCON outperforms the best known works in both computation and communication cost.