Y. Paek

HEPIC: Private Inference over Homomorphic Encryption with Client Intervention

Kevin Nam, Youyeon Joo, Seungjin Ha, Hyungon Moon et autres

Homomorphic Encryption (HE) enables Private Inference (PI) in Machine Learning as a Service (MLaaS), protecting both client inputs and server-side neural network (NN) parameters. Existing PI techniques are predominantly implemented as either HE-based fire-and-forget methods or MPC-based interactive methods. Recent HE-based PI …

kr (code pays fourni par la source)

Unified MEDS Accelerator

Sanjay Deshpande, Yongseok Lee, Mamuri Nawan, Kashif Nawaz et autres

us, kr, ae, dk, tw (code pays fourni par la source)

An Accelerator for Low-Computational Overhead Privacy-Preserving GNN Inference

Heonhui Jung, Whoi Ree Ha, Kevin Nam, Youyeon Joo et autres

Graph Neural Networks (GNNs) are increasingly used in domains such as finance and bioinformatics, where both node features and edge structures can contain sensitive information. While Fully Homomorphic Encryption (FHE) offers a promising solution for privacy-preserving GNN inference, existing approaches such as …

kr, fr (code pays fourni par la source)

Session details: System design issues

Y. Paek

No abstract available.

kr (code pays fourni par la source)