arXiv subjects

Hideki Takase

Publications and source records attributed to Hideki Takase.

5 recordsLinked to original sources

arXiv2026

CARVY-FL: Client Anticlustering for Robust Voting in Provably Secure Federated Learning

Federated learning (FL) enables collaborative training without directly sharing raw data, but remains vulnerable to malicious clients. Voting-based FL improves robustness by partitioning clients into groups, training one model per group, and aggregating predictions by plurality voting. However, under class-disjoint non-IID data, distribution-oblivious grouping can yield highly variable certified accuracy (CA). We propose CARVY-FL, which estimates client distribution types from one-epoch model updates and uses anticlustering to increase within-group distributional diversity. Under a fixed grouping, CARVY-FL retains the voting-based CA guarantee while increasing vote margins. Experiments on MNIST and Fashion-MNIST show higher CA than FLCert. Under BadNets with model replacement, CARVY-FL improves the AUC of 100-ASR by 11.1% and 14.9%, respectively.

cs.CR↗

arXiv2026

Dataflow-Oriented Classification and Performance Analysis of GPU-Accelerated Homomorphic Encryption

Fully Homomorphic Encryption (FHE) enables secure computation over encrypted data, but its computational cost remains a major obstacle to practical deployment. To mitigate this overhead, many studies have explored GPU acceleration for the CKKS scheme, which is widely used for approximate arithmetic. In CKKS, CKKS parameters are configured for each workload by balancing multiplicative depth, security requirements, and performance. These parameters significantly affect ciphertext size, thereby determining how the memory footprint fits within the GPU memory hierarchy. Nevertheless, prior studies typically apply their proposed optimization methods uniformly, without considering differences in CKKS parameter configurations. In this work, we demonstrate that the optimal GPU optimization strategy for CKKS depends on the CKKS parameter configuration. We first classify prior optimizations by two aspects of dataflows which affect memory footprint and then conduct both qualitative and quantitative performance analyses. Our analysis shows that even on the same GPU architecture, the optimal strategy varies with CKKS parameters with performance differences of up to 1.98 $\times$ between strategies, and that the criteria for selecting an appropriate strategy differ across GPU architectures.

cs.DC↗

arXiv2025

Hetero-SplitEE: Split Learning of Neural Networks with Early Exits for Heterogeneous IoT Devices

The continuous scaling of deep neural networks has fundamentally transformed machine learning, with larger models demonstrating improved performance across diverse tasks. This growth in model size has dramatically increased the computational resources required for the training process. Consequently, distributed approaches, such as Federated Learning and Split Learning, have become essential paradigms for scalable deployment. However, existing Split Learning approaches assume client homogeneity and uniform split points across all participants. This critically limits their applicability to real-world IoT systems where devices exhibit heterogeneity in computational resources. To address this limitation, this paper proposes Hetero-SplitEE, a novel method that enables heterogeneous IoT devices to train a shared deep neural network in parallel collaboratively. By integrating heterogeneous early exits into hierarchical training, our approach allows each client to select distinct split points (cut layers) tailored to its computational capacity. In addition, we propose two cooperative training strategies, the Sequential strategy and the Averaging strategy, to facilitate this collaboration among clients with different split points. The Sequential strategy trains clients sequentially with a shared server model to reduce computational overhead. The Averaging strategy enables parallel client training with periodic cross-layer aggregation. Extensive experiments on CIFAR-10, CIFAR-100, and STL-10 datasets using ResNet-18 demonstrate that our method maintains competitive accuracy while efficiently supporting diverse computational constraints, enabling practical deployment of collaborative deep learning in heterogeneous IoT ecosystems.

cs.LG↗

arXiv2025

Exploring the Possibility of TypiClust for Low-Budget Federated Active Learning

Federated Active Learning (FAL) seeks to reduce the burden of annotation under the realistic constraints of federated learning by leveraging Active Learning (AL). As FAL settings make it more expensive to obtain ground truth labels, FAL strategies that work well in low-budget regimes, where the amount of annotation is very limited, are needed. In this work, we investigate the effectiveness of TypiClust, a successful low-budget AL strategy, in low-budget FAL settings. Our empirical results show that TypiClust works well even in low-budget FAL settings contrasted with relatively low performances of other methods, although these settings present additional challenges, such as data heterogeneity, compared to AL. In addition, we show that FAL settings cause distribution shifts in terms of typicality, but TypiClust is not very vulnerable to the shifts. We also analyze the sensitivity of TypiClust to feature extraction methods, and it suggests a way to perform FAL even in limited data situations.

cs.LG↗

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↗