# SEALion: a Framework for Neural Network Inference on Encrypted Data

arXiv: https://arxiv.org/abs/1904.12840 · HTML: https://mlsanity.com/paper/1904.12840/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2019.

## Built on by (most cited first, 9 of 9)

- [Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network](https://mlsanity.com/paper/2106.07229/) (2021)
- [BlindFL: Vertical Federated Machine Learning without Peeking into Your Data](https://mlsanity.com/paper/2206.07975/) (2022)
- [HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption](https://mlsanity.com/paper/2403.14111/) (2024)
- [Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations](https://mlsanity.com/paper/2206.05893/) (2022)
- [Enabling Homomorphically Encrypted Inference for Large DNN Models](https://mlsanity.com/paper/2103.16139/) (2021)
- [AgenTEE: Confidential LLM Agent Execution on Edge Devices](https://mlsanity.com/paper/2604.18231/) (2026)
- [Partially Oblivious Neural Network Inference](https://mlsanity.com/paper/2210.15189/) (2022)
- [HE-MAN -- Homomorphically Encrypted MAchine learning with oNnx models](https://mlsanity.com/paper/2302.08260/) (2023)
- [FastFHE: Packing-Scalable and Depthwise-Separable CNN Inference Over FHE](https://mlsanity.com/paper/2511.22434/) (2025)

## Abstract (arXiv)

We present SEALion: an extensible framework for privacy-preserving machine learning with homomorphic encryption. It allows one to learn deep neural networks that can be seamlessly utilized for prediction on encrypted data. The framework consists of two layers: the first is built upon TensorFlow and SEAL and exposes standard algebra and deep learning primitives; the second implements a Keras-like syntax for training and inference with neural networks. Given a required level of security, a user is abstracted from the details of the encoding and the encryption scheme, allowing quick prototyping. We present two applications that exemplifying the extensibility of our proposal, which are also of independent interest: i) improving efficiency of neural network inference by an activity sparsifier and ii) transfer learning by querying a server-side Variational AutoEncoder that can handle encrypted data.