# PRISM: Privacy-preserving Inference System with Homomorphic Encryption and Modular Activation

arXiv: https://arxiv.org/abs/2511.07807 · HTML: https://mlsanity.com/paper/2511.07807/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 10 of 10)

- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network](https://mlsanity.com/paper/2106.07229/) (2021)
- [CryptoDL: Deep Neural Networks over Encrypted Data](https://mlsanity.com/paper/1711.05189/) (2017)
- [TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption](https://mlsanity.com/paper/2104.03152/) (2021)
- [Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference](https://mlsanity.com/paper/1811.09953/) (2018)
- [Precise Approximation of Convolutional Neural Networks for Homomorphically Encrypted Data](https://mlsanity.com/paper/2105.10879/) (2021)
- [POSEIDON: Privacy-Preserving Federated Neural Network Learning](https://mlsanity.com/paper/2009.00349/) (2020)
- [CIFAR-10: KNN-based Ensemble of Classifiers](https://mlsanity.com/paper/1611.04905/) (2016)
- [Highly Accurate CNN Inference Using Approximate Activation Functions over Homomorphic Encryption](https://mlsanity.com/paper/2009.03727/) (2020)
- [GALA: Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networks](https://mlsanity.com/paper/2105.01827/) (2021)

## Abstract (arXiv)

With the rapid advancements in machine learning, models have become increasingly capable of learning and making predictions in various industries. However, deploying these models in critical infrastructures presents a major challenge, as concerns about data privacy prevent unrestricted data sharing. Homomorphic encryption (HE) offers a solution by enabling computations on encrypted data, but it remains incompatible with machine learning models like convolutional neural networks (CNNs), due to their reliance on non-linear activation functions. To bridge this gap, this work proposes an optimized framework that replaces standard non-linear functions with homomorphically compatible approximations, ensuring secure computations while minimizing computational overhead. The proposed approach restructures the CNN architecture and introduces an efficient activation function approximation method to mitigate the performance trade-offs introduced by encryption. Experiments on CIFAR-10 achieve 94.4% accuracy with 2.42 s per single encrypted sample and 24,000 s per 10,000 encrypted samples, using a degree-4 polynomial and Softplus activation under CKKS, balancing accuracy and privacy.