15 papers
Alignment of Similarity-Transformed Images Based on Fourier--Mellin Transform Using Auxiliary Function Method
Shinji Yamashita, Yuma Kinoshita, Hitoshi Kiya
This paper proposes an algorithm for estimating the similarity transformation, namely translation, scale, and rotation, between two images with subpixel accuracy. Image registratio…
Boundary-Continuous Cross-Camera RGB Mapping via Hue-Split Model Trees
Yuma Kinoshita, Hitoshi Kiya
We propose a hue-split model-tree method for boundary-continuous cross-camera RGB mapping. Cross-camera RGB mapping aims to produce consistent color representations across cameras…
Voice Privacy Preservation with Multiple Random Orthogonal Secret Keys: Attack Resistance Analysis
Kohei Tanaka, Hitoshi Kiya, Sayaka Shiota
Recently, opportunities to transmit speech data to deep learning models executed in the cloud have increased. This has led to growing concerns about speech privacy, including both…
Scale and Rotation Estimation of Similarity-Transformed Images via Cross-Correlation Maximization Based on Auxiliary Function Method
Shinji Yamashita, Yuma Kinoshita, Hitoshi Kiya
This paper introduces a highly efficient algorithm capable of jointly estimating scale and rotation between two images with sub-pixel precision. Image alignment serves as a critica…
Scene-Segmentation-Based Exposure Compensation for Tone Mapping of High Dynamic Range Scenes
Yuma Kinoshita, Hitoshi Kiya
We propose a novel scene-segmentation-based exposure compensation method for multi-exposure image fusion (MEF) based tone mapping. The aim of MEF-based tone mapping is to display h…
Disposable-key-based image encryption for collaborative learning of Vision Transformer
Rei Aso, Sayaka Shiota, Hitoshi Kiya
We propose a novel method for securely training the vision transformer (ViT) with sensitive data shared from multiple clients similar to privacy-preserving federated learning. In t…
Speech privacy-preserving methods using secret key for convolutional neural network models and their robustness evaluation
Shoko Niwa, Sayaka Shiota, Hitoshi Kiya
In this paper, we propose privacy-preserving methods with a secret key for convolutional neural network (CNN)-based models in speech processing tasks. In environments where untrust…
Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation
AprilPyone MaungMaung, Huy H. Nguyen, Hitoshi Kiya +1
We propose a method for generating spurious features by leveraging large-scale text-to-image diffusion models. Although the previous work detects spurious features in a large-scale…
A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense
Ryota Iijima, Sayaka Shiota, Hitoshi Kiya
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In previous studies, the use of models encrypted with a secret key was demonstrated to be…
Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer
Teru Nagamori, Sayaka Shiota, Hitoshi Kiya
We propose a novel method for privacy-preserving deep neural networks (DNNs) with the Vision Transformer (ViT). The method allows us not only to train models and test with visually…
A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examples
Ryota Iijima, Sayaka Shiota, Hitoshi Kiya
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source…
Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Model
AprilPyone MaungMaung, Isao Echizen, Hitoshi Kiya
In this paper, we propose key-based defense model proliferation by leveraging pre-trained models and utilizing recent efficient fine-tuning techniques on ImageNet-1k classification…
A privacy-preserving method using secret key for convolutional neural network-based speech classification
Shoko Niwa, Sayaka Shiota, Hitoshi Kiya
In this paper, we propose a privacy-preserving method with a secret key for convolutional neural network (CNN)-based speech classification tasks. Recently, many methods related to…
Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Images
Teru Nagamori, Sayaka Shiota, Hitoshi Kiya
In recent years, deep neural networks (DNNs) trained with transformed data have been applied to various applications such as privacy-preserving learning, access control, and advers…
Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddings
AprilPyone MaungMaung, Isao Echizen, Hitoshi Kiya
In this paper, we propose a new key-based defense focusing on both efficiency and robustness. Although the previous key-based defense seems effective in defending against adversari…