EP-HDC: Hyperdimensional Computing with Encrypted Parameters for High-Throughput Privacy-Preserving Inference
This addresses privacy-preserving inference for machine learning applications, offering high scalability and strong data protection, though it is incremental as it builds on existing HDC and HE techniques.
The paper tackles the high computational cost and overhead of privacy-preserving machine learning in batch inference scenarios by proposing EP-HDC, a method using hyperdimensional computing with encrypted parameters, which improves throughput and latency by orders of magnitude (36.52~1068x and 6.45~733x) with minimal accuracy loss (<1%).
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.