arXiv subjects

Hitoshi Kiya

Publications and source records attributed to Hitoshi Kiya.

At least 91 records · Page 5Linked to original sources

arXiv2021

Deep Retinex Network for Estimating Illumination Colors with Self-Supervised Learning

We propose a novel Retinex image-decomposition network that can be trained in a self-supervised manner. The Retinex image-decomposition aims to decompose an image into illumination-invariant and illumination-variant components, referred to as "reflectance" and "shading," respectively. Although there are three consistencies that the reflectance and shading should satisfy, most conventional work considers only one or two of the consistencies. For this reason, the three consistencies are considered in the proposed network. In addition, by using generated pseudo-images for training, the proposed network can be trained with self-supervised learning. Experimental results show that our network can decompose images into reflectance and shading components. Furthermore, it is shown that the proposed network can be used for white-balance adjustment.

eess.IV↗

arXiv2021

Fake-image detection with Robust Hashing

In this paper, we investigate whether robust hashing has a possibility to robustly detect fake-images even when multiple manipulation techniques such as JPEG compression are applied to images for the first time. In an experiment, the proposed fake detection with robust hashing is demonstrated to outperform state-of-the-art one under the use of various datasets including fake images generated with GANs.

cs.MM↗

arXiv2020

Difficulty in estimating visual information from randomly sampled images

In this paper, we evaluate dimensionality reduction methods in terms of difficulty in estimating visual information on original images from dimensionally reduced ones. Recently, dimensionality reduction has been receiving attention as the process of not only reducing the number of random variables, but also protecting visual information for privacy-preserving machine learning. For such a reason, difficulty in estimating visual information is discussed. In particular, the random sampling method that was proposed for privacy-preserving machine learning, is compared with typical dimensionality reduction methods. In an image classification experiment, the random sampling method is demonstrated not only to have high difficulty, but also to be comparable to other dimensionality reduction methods, while maintaining the property of spatial information invariant.

cs.CV↗

arXiv2020

CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection

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 image synthesis techniques, such as Generative Adversarial Networks (GANs) have easily generated fake images, so detecting manipulated images has become an urgent issue. Most state-of-the-art forgery detection methods assume that images include checkerboard artifacts which are generated by using DNNs. Accordingly, we propose a novel CycleGAN without any checkerboard artifacts for counter-forensics of fake-mage detection methods for the first time, as an example of GANs without checkerboard artifacts.

cs.CV↗

arXiv2020

A Reversible Data Hiding Method in Compressible Encrypted Images

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 embed a payload in encrypted images but also compress the encrypted images containing the payload. In addition, the proposed RDH method can be applied to both plain images and encrypted ones, and the payload can be extracted flexibly in the encrypted domain or from the decrypted images. Various RDH methods have been studied in the encrypted domain, but they are not considered to be two-domain data hiding, and the resultant images cannot be compressed by using image coding standards, such as JPEG-LS and JPEG 2000. In our experiment, the proposed method shows high performance in terms of lossless compression efficiency by using JPEG-LS and JPEG 2000, data hiding capacity, and marked image quality.

cs.CR↗

arXiv2020

A Block-Permutation-Based Encryption Scheme with Independent Processing of RGB Components

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 obtained through four processes, positional scrambling, block rotation/flip, negative-positive transformation, and color component shuffling, after dividing the original image into multiple blocks. The proposed scheme scrambles the R, G, and B components independently in positional scrambling, block rotation/flip, and negative-positive transformation, by assigning different keys to each color component. The conventional scheme considers the compression efficiency using JPEG and JPEG 2000, which need a color conversion before the compression process by default. Therefore, the conventional scheme scrambles the color components identically in each process. In contrast, the proposed scheme takes into account the RGB-based compression, such as JPEG-LS, and thus can increase the extent of the scrambling. The resilience against jigsaw puzzle solver (JPS) can consequently be increased owing to the wider color distribution of the BPBE image. Additionally, the key space for resilience against brute-force attacks has also been expanded exponentially. Furthermore, the proposed scheme can maintain the JPEG-LS compression efficiency compared to the conventional scheme. We confirm the effectiveness of the proposed scheme by experiments and analyses.

cs.MM↗

arXiv2020

Ensemble of Models Trained by Key-based Transformed Images for Adversarially Robust Defense Against Black-box Attacks

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 demonstrated to outperform state-of-the-art defenses against gradient-based (white-box) attacks. However, the key-based defenses are not effective enough against gradient-free (black-box) attacks without requiring any secret keys. Accordingly, we aim to enhance robustness against black-box attacks by using a voting ensemble of models. In the proposed ensemble, a number of models are trained by using images transformed with different keys and block sizes, and then a voting ensemble is applied to the models. In image classification experiments, the proposed defense is demonstrated to defend state-of-the-art attacks. The proposed defense achieves a clean accuracy of 95.56 % and an attack success rate of less than 9 % under attacks with a noise distance of 8/255 on the CIFAR-10 dataset.

cs.CV↗

arXiv2020

A Privacy-Preserving Content-Based Image Retrieval Scheme Allowing Mixed Use Of Encrypted And Plain Images

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 encrypted by a block-scrambling method developed for encryption-then-compression (EtC) systems. The encrypted images, referred to as EtC images, can be compressed with JPEG, as well as for plain images. Image descriptors used for the proposed retrieval is designed to avoid the effect of image encryption. As a result, the use of EtC images and the descriptors allows us to carry out retrieval of both encrypted images and plain ones. In an experiment, the proposed scheme is demonstrated to have the same performance as conventional retrieval methods with plain images, even under the mixed use of plain images and EtC ones.

eess.IV↗

arXiv2020

Visual Security Evaluation of Learnable Image Encryption Methods against Ciphertext-only Attacks

Various visual information protection methods have been proposed for privacy-preserving deep neural networks (DNNs). In contrast, attack methods on such protection methods have been studied simultaneously. In this paper, we evaluate state-of-the-art visual protection methods for privacy-preserving DNNs in terms of visual security against ciphertext-only attacks (COAs). We focus on brute-force attack, feature reconstruction attack (FR-Attack), inverse transformation attack (ITN-Attack), and GAN-based attack (GAN-Attack), which have been proposed to reconstruct visual information on plain images from the visually-protected images. The detail of various attack is first summarized, and then visual security of the protection methods is evaluated. Experimental results demonstrate that most of protection methods, including pixel-wise encryption, have not enough robustness against GAN-Attack, while a few protection methods are robust enough against GAN-Attack.

cs.CR↗

arXiv2020

Checkerboard-Artifact-Free Image-Enhancement Network Considering Local and Global Features

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 translation problems, it is well-known that images generated by usual CNNs are distorted by checkerboard artifacts which mainly caused in forward-propagation of upsampling layers. However, checkerboard artifacts in image enhancement have never been discussed. In this paper, we point out that applying U-Net based CNNs to image enhancement causes checkerboard artifacts. In contrast, the proposed network that contains fixed convolutional layers can perfectly prevent the artifacts. In addition, the proposed network architecture, which can handle both local and global features, enables us to improve the performance of image enhancement. Experimental results show that the use of fixed convolutional layers can prevent checkerboard artifacts and the proposed network outperforms state-of-the-art CNN-based image-enhancement methods in terms of various objective quality metrics: PSNR, SSIM, and NIQE.

eess.IV↗

arXiv2020

Block-wise Image Transformation with Secret Key for Adversarially Robust Defense

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 for adversarially robust defense. The proposed transformation is a block-wise preprocessing technique with a secret key to input images. We developed three algorithms to realize the proposed transformation: Pixel Shuffling, Bit Flipping, and FFX Encryption. Experiments were carried out on the CIFAR-10 and ImageNet datasets by using both black-box and white-box attacks with various metrics including adaptive ones. The results show that the proposed defense achieves high accuracy close to that of using clean images even under adaptive attacks for the first time. In the best-case scenario, a model trained by using images transformed by FFX Encryption (block size of 4) yielded an accuracy of 92.30% on clean images and 91.48% under PGD attack with a noise distance of 8/255, which is close to the non-robust accuracy (95.45%) for the CIFAR-10 dataset, and it yielded an accuracy of 72.18% on clean images and 71.43% under the same attack, which is also close to the standard accuracy (73.70%) for the ImageNet dataset. Overall, all three proposed algorithms are demonstrated to outperform state-of-the-art defenses including adversarial training whether or not a model is under attack.

cs.CV↗

arXiv2020

Extension of JPEG XS for Two-Layer Lossless Coding

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 low latency and very low complexity. However, it does not support lossless coding, although it can achieve visual lossless coding. The proposed method has a two-layer structure similar to JPEG XT, which consists of JPEG XS coding and a lossless coding method. As a result, it enables us to losslessly restore original images, while maintaining compatibility with JPEG XS.

cs.MM↗

arXiv2020

Image Transformation Network for Privacy-Preserving Deep Neural Networks and Its Security Evaluation

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 dataset so that plain images are transformed into visually protected ones. Conventional perceptual encryption methods have a weak visual-protection performance and some accuracy degradation in image classification. In contrast, the proposed network enables us not only to strongly protect visual information but also to maintain the image classification accuracy that using plain images achieves. In an image classification experiment, the proposed network is demonstrated to strongly protect visual information on plain images without any performance degradation under the use of CIFAR datasets. In addition, it is shown that the visually protected images are robust against a DNN-based attack, called inverse transformation network attack (ITN-Attack) in an experiment.

eess.IV↗

arXiv2020

Training DNN Model with Secret Key for Model Protection

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 protected model is built by training with such preprocessed images. Experiment results show that the performance of the protected model is close to that of non-protected models when the key is correct, while the accuracy is severely dropped when an incorrect key is given, and the proposed model protection is robust against not only brute-force attacks but also fine-tuning attacks, while maintaining almost the same performance accuracy as that of using a non-protected model.

cs.LG↗

arXiv2020

Hue-Correction Scheme Considering Non-Linear Camera Response for Multi-Exposure Image Fusion

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 few MEF methods considering hue distortion unlike other fields of image processing, due to a lack of a reference image that has correct hue. In the proposed scheme, we generate an HDR image as a reference for hue correction, from input multi-exposure images. After that, hue distortion in images fused by an MEF method is removed by using hue information of the HDR one, on the basis of the constant-hue plane in the RGB color space. In simulations, the proposed scheme is demonstrated to be effective to correct hue-distortion caused by conventional MEF methods. Experimental results also show that the proposed scheme can generate high-quality images, regardless of exposure conditions of input multi-exposure images.

eess.IV↗

arXiv2020

A Privacy-Preserving Machine Learning Scheme Using EtC Images

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 method proposed for EtC systems with JPEG compression. In this paper, a novel property of EtC images is first discussed, although EtC ones was already shown to be compressible as a property. The novel property allows us to directly apply EtC images to machine learning algorithms non-specialized for computing encrypted data. In addition, the proposed scheme is demonstrated to provide no degradation in the performance of some typical machine learning algorithms including the support vector machine algorithm with kernel trick and random forests under the use of z-score normalization. A number of facial recognition experiments with are carried out to confirm the effectiveness of the proposed scheme.

cs.CR↗

arXiv2020

A GAN-Based Image Transformation Scheme for Privacy-Preserving Deep Neural Networks

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 only to apply images without visual information to DNNs, but also to enhance robustness against ciphertext-only attacks (COAs) including DNN-based attacks. In this paper, the proposed transformation scheme is demonstrated to be able to protect visual information on plain images, and the visually-protected images are directly applied to DNNs for privacy-preserving image classification. Since the proposed scheme utilizes GANs, there is no need to manage encryption keys. In an image classification experiment, we evaluate the effectiveness of the proposed scheme in terms of classification accuracy and robustness against COAs.

cs.CR↗

arXiv2020

Encryption Inspired Adversarial Defense for Visual Classification

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 problem of obfuscated gradients. In this paper, we propose a new adversarial defense which is a defensive transform for both training and test images inspired by perceptual image encryption methods. The proposed method utilizes a block-wise pixel shuffling method with a secret key. The experiments are carried out on both adaptive and non-adaptive maximum-norm bounded white-box attacks while considering obfuscated gradients. The results show that the proposed defense achieves high accuracy (91.55 %) on clean images and (89.66 %) on adversarial examples with noise distance of 8/255 on CIFAR-10 dataset. Thus, the proposed defense outperforms state-of-the-art adversarial defenses including latent adversarial training, adversarial training and thermometer encoding.

cs.LG↗