# EP-HDC: Hyperdimensional Computing with Encrypted Parameters for High-Throughput Privacy-Preserving Inference

arXiv: https://arxiv.org/abs/2511.00737 · HTML: https://mlsanity.com/paper/2511.00737/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 1 Nov 2025.

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

- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [Low Latency Privacy Preserving Inference](https://mlsanity.com/paper/1812.10659/) (2018)
- [Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference](https://mlsanity.com/paper/1811.09953/) (2018)
- [A Theoretical Perspective on Hyperdimensional Computing](https://mlsanity.com/paper/2010.07426/) (2020)
- [ARK: Fully Homomorphic Encryption Accelerator with Runtime Data Generation and Inter-Operation Key Reuse](https://mlsanity.com/paper/2205.00922/) (2022)
- [Prive-HD: Privacy-Preserved Hyperdimensional Computing](https://mlsanity.com/paper/2005.06716/) (2020)
- [FHEBench: Benchmarking Fully Homomorphic Encryption Schemes](https://mlsanity.com/paper/2203.00728/) (2022)
- [Hyperdimensional Computing as a Rescue for Efficient Privacy-Preserving Machine Learning-as-a-Service](https://mlsanity.com/paper/2310.06840/) (2023)
- [NTT-PIM: Row-Centric Architecture and Mapping for Efficient Number-Theoretic Transform on PIM](https://mlsanity.com/paper/2310.09715/) (2023)

## Abstract (arXiv)

While homomorphic encryption (HE) provides strong privacy protection, its high computational cost has restricted its application to simple tasks. Recently, hyperdimensional computing (HDC) applied to HE has shown promising performance for privacy-preserving machine learning (PPML). However, when applied to more realistic scenarios such as batch inference, the HDC-based HE has still very high compute time as well as high encryption and data transmission overheads. To address this problem, we propose HDC with encrypted parameters (EP-HDC), which is a novel PPML approach featuring client-side HE, i.e., inference is performed on a client using a homomorphically encrypted model. Our EP-HDC can effectively mitigate the encryption and data transmission overhead, as well as providing high scalability with many clients while providing strong protection for user data and model parameters. In addition to application examples for our client-side PPML, we also present design space exploration involving quantization, architecture, and HE-related parameters. Our experimental results using the BFV scheme and the Face/Emotion datasets demonstrate that our method can improve throughput and latency of batch inference by orders of magnitude over previous PPML methods (36.52~1068x and 6.45~733x, respectively) with less than 1% accuracy degradation.