# PADER: Paillier-based Secure Decentralized Social Recommendation

arXiv: https://arxiv.org/abs/2601.10212 · HTML: https://mlsanity.com/paper/2601.10212/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 68 references that are in the map.
- First posted on arXiv 15 Jan 2026.

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

- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [Secure Federated Matrix Factorization](https://mlsanity.com/paper/1906.05108/) (2019)
- [HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data](https://mlsanity.com/paper/2011.01805/) (2020)
- [Decentralized Collaborative Learning Framework for Next POI Recommendation](https://mlsanity.com/paper/2204.06516/) (2022)
- [Privacy Preserving Point-of-interest Recommendation Using Decentralized Matrix Factorization](https://mlsanity.com/paper/2003.05610/) (2020)
- [Private Computation of Polynomials over Networks](https://mlsanity.com/paper/2104.01369/) (2021)

## Abstract (arXiv)

The prevalence of recommendation systems also brings privacy concerns to both the users and the sellers, as centralized platforms collect as much data as possible from them. To keep the data private, we propose PADER: a Paillier-based secure decentralized social recommendation system. In this system, the users and the sellers are nodes in a decentralized network. The training and inference of the recommendation model are carried out securely in a decentralized manner, without the involvement of a centralized platform. To this end, we apply the Paillier cryptosystem to the SoReg (Social Regularization) model, which exploits both user's ratings and social relations. We view the SoReg model as a two-party secure polynomial evaluation problem and observe that the simple bipartite computation may result in poor efficiency. To improve efficiency, we design secure addition and multiplication protocols to support secure computation on any arithmetic circuit, along with an optimal data packing scheme that is suitable for the polynomial computations of real values. Experiment results show that our method only takes about one second to iterate through one user with hundreds of ratings, and training with ~500K ratings for one epoch only takes <3 hours, which shows that the method is practical in real applications. The code is available at https://github.com/GarminQ/PADER.