4 papers
Scaling up FHE-based Privacy-Preserving ML: Higher Throughput, Longer Inputs for LLama-3-8B
Jaiyoung Park, Sejin Park, Jai Hyun Park +6
As large language models (LLMs) become ubiquitous, privacy concerns pertaining to inference keep growing. Fully homomorphic encryption (FHE) has emerged as a primary cryptographic…
Hardware-efficient quantum error correction via concatenated bosonic qubits
Harald Putterman, Kyungjoo Noh, Connor T. Hann +118
In order to solve problems of practical importance, quantum computers will likely need to incorporate quantum error correction, where a logical qubit is redundantly encoded in many…
Encryption-Friendly LLM Architecture
Donghwan Rho, Taeseong Kim, Minje Park +4
Large language models (LLMs) offer personalized responses based on user interactions, but this use case raises serious privacy concerns. Homomorphic encryption (HE) is a cryptograp…
Fast and Accurate Homomorphic Softmax Evaluation
Wonhee Cho, Guillaume Hanrot, Taeseong Kim +2
Homomorphic encryption is one of the main solutions for building secure and privacy-preserving solutions for Machine Learning as a Service. This motivates the development of homomo…