arXiv subjects

Masato Oguchi

Publications and source records attributed to Masato Oguchi.

2 recordsLinked to original sources

arXiv2025

TFHE-SBC: Software Designs for Fully Homomorphic Encryption over the Torus on Single Board Computers

Fully homomorphic encryption (FHE) is a technique that enables statistical processing and machine learning while protecting data, including sensitive information collected by single board computers (SBCs), on a cloud server. Among FHE schemes, the TFHE scheme is capable of homomorphic NAND operations and, unlike other FHE schemes, can perform various operations such as minimum, maximum, and comparison. However, TFHE requires Torus Learning With Error (TLWE) encryption, which encrypts one bit at a time, leading to less efficient encryption and larger ciphertext size compared to other schemes. Additionally, SBCs have a limited number of hardware accelerators compared to servers, making it challenging to achieve the same level of optimization as on servers. In this study, we propose a novel SBC-specific design, \textsf{TFHE-SBC}, to accelerate client-side TFHE operations and enhance communication and energy efficiency. Experimental results demonstrate that \textsf{TFHE-SBC} encryption is up to 2486 times faster, improves communication efficiency by 512 times, and achieves 12 to 2004 times greater energy efficiency than the state-of-the-art.

cs.CR↗

arXiv2022

Measuring Lower Bounds of Local Differential Privacy via Adversary Instantiations in Federated Learning

Local differential privacy (LDP) gives a strong privacy guarantee to be used in a distributed setting like federated learning (FL). LDP mechanisms in FL protect a client's gradient by randomizing it on the client; however, how can we interpret the privacy level given by the randomization? Moreover, what types of attacks can we mitigate in practice? To answer these questions, we introduce an empirical privacy test by measuring the lower bounds of LDP. The privacy test estimates how an adversary predicts if a reported randomized gradient was crafted from a raw gradient $g_1$ or $g_2$. We then instantiate six adversaries in FL under LDP to measure empirical LDP at various attack surfaces, including a worst-case attack that reaches the theoretical upper bound of LDP. The empirical privacy test with the adversary instantiations enables us to interpret LDP more intuitively and discuss relaxation of the privacy parameter until a particular instantiated attack surfaces. We also demonstrate numerical observations of the measured privacy in these adversarial settings, and the worst-case attack is not realistic in FL. In the end, we also discuss the possible relaxation of privacy levels in FL under LDP.

cs.CR↗