71 citations · 304 across the 98 of their papers we have counts for
18 papers · 1 filter
Difficulty in estimating visual information from randomly sampled images
Masaki Kitayama, Hitoshi Kiya
In this paper, we evaluate dimensionality reduction methods in terms of difficulty in estimating visual information on original images from dimensionally reduced ones. Recently, di…
CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection
Takayuki Osakabe, Miki Tanaka, Yuma Kinoshita +1
In this paper, we propose a novel CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection. Recent rapid advances in image manipulation tools and deep…
A Reversible Data Hiding Method in Compressible Encrypted Images
Shoko Imaizumi, Yusuke Izawa, Ryoichi Hirasawa +1
We propose a reversible data hiding (RDH) method in compressible encrypted images called the encryption-then-compression (EtC) images. The proposed method allows us to not only emb…
A Block-Permutation-Based Encryption Scheme with Independent Processing of RGB Components
Shoko Imaizumi, Hitoshi Kiya
This paper proposes a block-permutation-based encryption (BPBE) scheme for the encryption-then-compression (ETC) system that enhances the color scrambling. A BPBE image can be obta…
Ensemble of Models Trained by Key-based Transformed Images for Adversarially Robust Defense Against Black-box Attacks
MaungMaung AprilPyone, Hitoshi Kiya
We propose a voting ensemble of models trained by using block-wise transformed images with secret keys for an adversarially robust defense. Key-based adversarial defenses were demo…
A Privacy-Preserving Content-Based Image Retrieval Scheme Allowing Mixed Use Of Encrypted And Plain Images
Kenta Iida, Hitoshi Kiya
In this paper, we propose a novel content based-image retrieval scheme allowing the mixed use of encrypted and plain images for the first time. In the proposed scheme, images are e…
Checkerboard-Artifact-Free Image-Enhancement Network Considering Local and Global Features
Yuma Kinoshita, Hitoshi Kiya
In this paper, we propose a novel convolutional neural network (CNN) that never causes checkerboard artifacts, for image enhancement. In research fields of image-to-image translati…
Visual Security Evaluation of Learnable Image Encryption Methods against Ciphertext-only Attacks
Warit Sirichotedumrong, Hitoshi Kiya
Various visual information protection methods have been proposed for privacy-preserving deep neural networks (DNNs). In contrast, attack methods on such protection methods have bee…
Block-wise Image Transformation with Secret Key for Adversarially Robust Defense
MaungMaung AprilPyone, Hitoshi Kiya
In this paper, we propose a novel defensive transformation that enables us to maintain a high classification accuracy under the use of both clean images and adversarial examples fo…
Extension of JPEG XS for Two-Layer Lossless Coding
Hiroyuki Kobayashi, Hitoshi Kiya
A two-layer lossless image coding method compatible with JPEG XS is proposed. JPEG XS is a new international standard for still image coding that has the characteristics of very lo…
Image Transformation Network for Privacy-Preserving Deep Neural Networks and Its Security Evaluation
Hiroki Ito, Yuma Kinoshita, Hitoshi Kiya
We propose a transformation network for generating visually-protected images for privacy-preserving DNNs. The proposed transformation network is trained by using a plain image data…
Training DNN Model with Secret Key for Model Protection
MaungMaung AprilPyone, Hitoshi Kiya
In this paper, we propose a model protection method by using block-wise pixel shuffling with a secret key as a preprocessing technique to input images for the first time. The prote…
Hue-Correction Scheme Considering Non-Linear Camera Response for Multi-Exposure Image Fusion
Kouki Seo, Chihiro Go, Yuma Kinoshita +1
We propose a novel hue-correction scheme for multi-exposure image fusion (MEF). Various MEF methods have so far been studied to generate higher-quality images. However, there are f…
A Privacy-Preserving Machine Learning Scheme Using EtC Images
Ayana Kawamura, Yuma Kinoshita, Takayuki Nakachi +2
We propose a privacy-preserving machine learning scheme with encryption-then-compression (EtC) images, where EtC images are images encrypted by using a block-based encryption metho…
A GAN-Based Image Transformation Scheme for Privacy-Preserving Deep Neural Networks
Warit Sirichotedumrong, Hitoshi Kiya
We propose a novel image transformation scheme using generative adversarial networks (GANs) for privacy-preserving deep neural networks (DNNs). The proposed scheme enables us not o…
Encryption Inspired Adversarial Defense for Visual Classification
MaungMaung AprilPyone, Hitoshi Kiya
Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the…
Hue Correction Scheme for Multi-Exposure Image Fusion Considering Hue Distortion in Input Images
Kouki Seo, Chihiro Go, Yuma Kinoshita +1
We propose a novel hue-correction scheme for multi-exposure image fusion (MEF). Various MEF methods have so far been studied to generate higher-quality images. However, there are f…
Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs
Yuma Kinoshita, Hitoshi Kiya
In this paper, we propose a fixed convolutional layer with an order of smoothness not only for avoiding checkerboard artifacts in convolutional neural networks (CNNs) but also for…