Hirohisa Aman

Shozo Saeki, Minoru Kawahara, Hirohisa Aman

A nearest-neighbor framework is a fundamental tool for various applications involving Large Language Models (LLMs) and Visual Language Models (VLMs). Vectors used for nearest-neighbor searches have richer information for similarity searches. This information leads to security risks, such as embedding inversion and membership attacks. Therefore, Privacy-Preserving Approximate Nearest-Neighbor (PP-ANN) approaches are necessary for highly confidential data. However, conventional PP-ANN approaches based on a Trusted Execution Environment (TEE) or Fully Homomorphic Encryption (FHE) do not achieve practical security or performance. Additionally, conventional approaches focus on the search process rather than database generation for nearest-neighbor. To address these issues, we propose a Privacy-Preserving Product-Quantization Approximate Nearest Neighbor (PPPQ-ANN) framework. PPPQ-ANN provides a multi-layered security structure for vectors based on a hybrid of FHE and TEE. Additionally, PPPQ-ANN minimizes FHE ciphertext computations by combining Product-Quantization (PQ) with optimized data packing. We demonstrate the performance of PPPQ-ANN on million-scale datasets. As a result, PPPQ-ANN achieves database generation in less than 2 hours and more than 50 QPS in a sequential search while preserving privacy. Therefore, PPPQ-ANN optimizes the trade-off between security and performance by utilizing a hybrid of FHE and TEE, achieving practical performance while preserving privacy.

Shozo Saeki, Minoru Kawahara, Hirohisa Aman

Deep metric learning (DML) aims to learn a neural network mapping data to an embedding space, which can represent semantic similarity between data points. Hyperbolic space is attractive for DML since it can represent richer structures, such as tree structures. DML in hyperbolic space is based on pair-based loss or unsupervised regularization loss. On the other hand, supervised proxy-based losses in hyperbolic space have not been reported yet due to some issues in applying proxy-based losses in a hyperbolic space. However, proxy-based losses are attractive for large-scale datasets since they have less training complexity. To address these, this paper proposes the Combined Hyperbolic and Euclidean Soft Triple (CHEST) loss. CHEST loss is composed of the proxy-based losses in hyperbolic and Euclidean spaces and the regularization loss based on hyperbolic hierarchical clustering. We find that the combination of hyperbolic and Euclidean spaces improves DML accuracy and learning stability for both spaces. Finally, we evaluate the CHEST loss on four benchmark datasets, achieving a new state-of-the-art performance.

Shozo Saeki, Minoru Kawahara, Hirohisa Aman

The deep metric learning (DML) objective is to learn a neural network that maps into an embedding space where similar data are near and dissimilar data are far. However, conventional proxy-based losses for DML have two problems: gradient problem and application of the real-world dataset with multiple local centers. Additionally, the performance metrics of DML also have some issues with stability and flexibility. This paper proposes three multi-proxies anchor (MPA) family losses and a normalized discounted cumulative gain (nDCG@k) metric. This paper makes three contributions. (1) MPA-family losses can learn using a real-world dataset with multi-local centers. (2) MPA-family losses improve the training capacity of a neural network owing to solving the gradient problem. (3) MPA-family losses have data-wise or class-wise characteristics with respect to gradient generation. Finally, we demonstrate the effectiveness of MPA-family losses, and MPA-family losses achieves higher accuracy on two datasets for fine-grained images.