Search Results for author:
Found 76 papers, 2 papers with code
Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation
To this end, we utilize an existing approach of personalizing large-scale text-to-image diffusion models with available discovered spurious images and propose a new spurious feature similarity loss based on neural features of an adversarially robust model.
A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs).
Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer
We propose a novel method for privacy-preserving deep neural networks (DNNs) with the Vision Transformer (ViT).
A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examples
In previous studies, it was confirmed that the vision transformer (ViT) is more robust against the property of adversarial transferability than convolutional neural network (CNN) models such as ConvMixer, and moreover encrypted ViT is more robust than ViT without any encryption.
Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Model
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
To promote research on privacy preservation for speech classification, we provide an encryption method with a secret key in CNN-based speech classification systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Domain Adaptation for Efficiently Fine-tuning Vision Transformer with Encrypted Images
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 adversarial defenses.
Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddings
In this paper, we propose a new key-based defense focusing on both efficiency and robustness.
Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Models
In previous studies, it was confirmed that the vision transformer (ViT) is more robust against the property of adversarial transferability than convolutional neural network (CNN) models such as ConvMixer, and moreover encrypted ViT is more robust than ViT without any encryption.
Generative Model-Based Attack on Learnable Image Encryption for Privacy-Preserving Deep Learning
By taking advantage of leaked information from encrypted images, we propose a guided generative model as an attack on learnable image encryption to recover personally identifiable visual information.
Combined Use of Federated Learning and Image Encryption for Privacy-Preserving Image Classification with Vision Transformer
In recent years, privacy-preserving methods for deep learning have become an urgent problem.
Color-NeuraCrypt: Privacy-Preserving Color-Image Classification Using Extended Random Neural Networks
In recent years, with the development of cloud computing platforms, privacy-preserving methods for deep learning have become an urgent problem.
A Privacy Preserving Method with a Random Orthogonal Matrix for ConvMixer Models
In this paper, a privacy preserving image classification method is proposed under the use of ConvMixer models.
Access Control with Encrypted Feature Maps for Object Detection Models
In an experiment, the protected models allowed authorized users to obtain almost the same performance as that of non-protected models but also with robustness against unauthorized access without a key.
On the Adversarial Transferability of ConvMixer Models
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs).
StyleGAN Encoder-Based Attack for Block Scrambled Face Images
In this paper, we propose an attack method to block scrambled face images, particularly Encryption-then-Compression (EtC) applied images by utilizing the existing powerful StyleGAN encoder and decoder for the first time.
On the Transferability of Adversarial Examples between Encrypted Models
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs).
An Access Control Method with Secret Key for Semantic Segmentation Models
A novel method for access control with a secret key is proposed to protect models from unauthorized access in this paper.
A Detection Method of Temporally Operated Videos Using Robust Hashing
In addition, videos are temporally operated such as the insertion of new frames and the permutation of frames, of which operations are difficult to be detected by using conventional methods.
Privacy-Preserving Image Classification Using ConvMixer with Adaptive Permutation Matrix
In this paper, we propose a privacy-preserving image classification method using encrypted images under the use of the ConvMixer structure.
Template matching with white balance adjustment under multiple illuminants
In this paper, we propose a novel template matching method with a white balancing adjustment, called N-white balancing, which was proposed for multi-illuminant scenes.
An Encryption Method of ConvMixer Models without Performance Degradation
In an experiment, the effectiveness of the proposed method is evaluated in terms of classification accuracy and model protection in an image classification task on the CIFAR10 dataset.
Image and Model Transformation with Secret Key for Vision Transformer
In this paper, we propose a combined use of transformed images and vision transformer (ViT) models transformed with a secret key.
Access Control of Semantic Segmentation Models Using Encrypted Feature Maps
In this paper, we propose an access control method with a secret key for semantic segmentation models for the first time so that unauthorized users without a secret key cannot benefit from the performance of trained models.
Privacy-Preserving Image Classification Using Vision Transformer
In this paper, we propose a privacy-preserving image classification method that is based on the combined use of encrypted images and the vision transformer (ViT).
Privacy-Preserving Image Classification Using Isotropic Network
In addition, compressible encrypted images, called encryption-then-compression (EtC) images, can be used for both training and testing without any adaptation network.
On the predictability in reversible steganography
The core strength of neural networks is the ability to render accurate predictions for a bewildering variety of data.
Adversarial Detector with Robust Classifier
Deep neural network (DNN) models are wellknown to easily misclassify prediction results by using input images with small perturbations, called adversarial examples.
A Privacy-Preserving Image Retrieval Scheme with a Mixture of Plain and EtC Images
In this paper, we propose a novel content-based image-retrieval scheme that allows us to use a mixture of plain images and compressible encrypted ones called "encryption-then-compression (EtC) images."
Access Control of Object Detection Models Using Encrypted Feature Maps
In this paper, the use of encrypted feature maps is shown to be effective in access control of object detection models for the first time.
An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications
In this paper, we focus on a class of image transformation referred to as learnable image encryption, which is applicable to privacy-preserving machine learning and adversarially robust defense.
Protection of SVM Model with Secret Key from Unauthorized Access
In this paper, we propose a block-wise image transformation method with a secret key for support vector machine (SVM) models.
Self-Supervised Intrinsic Image Decomposition Network Considering Reflectance Consistency
Intrinsic image decomposition aims to decompose an image into illumination-invariant and illumination-variant components, referred to as ``reflectance'' and ``shading,'' respectively.
A Privacy-Preserving Image Retrieval Scheme Using A Codebook Generated From Independent Plain-Image Dataset
In an experiment, the proposed scheme is demonstrated to maintain a high retrieval performance, even if codebooks are generated from a plain image dataset independent of image owners' encrypted images.
Spatially varying white balancing for mixed and non-uniform illuminants
In this paper, we propose a novel white balance adjustment, called "spatially varying white balancing," for single, mixed, and non-uniform illuminants.
Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Models
In an experiment, the protected models were demonstrated to allow rightful users to obtain almost the same performance as that of non-protected models but also to be robust against access by unauthorized users without a key.
A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Access
In this paper, we propose a model protection method for convolutional neural networks (CNNs) with a secret key so that authorized users get a high classification accuracy, and unauthorized users get a low classification accuracy.
A universal detector of CNN-generated images using properties of checkerboard artifacts in the frequency domain
In addition, an ensemble of the proposed detector with emphasized spectrums and a conventional detector is proposed to improve the performance of these methods.
Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Access
Since production-level trained deep neural networks (DNNs) are of a great business value, protecting such DNN models against copyright infringement and unauthorized access is in a rising demand.
Separated-Spectral-Distribution Estimation Based on Bayesian Inference with Single RGB Camera
In this paper, we propose a novel method for separately estimating spectral distributions from images captured by a typical RGB camera.
A Protection Method of Trained CNN Model with Secret Key from Unauthorized Access
In this paper, we propose a novel method for protecting convolutional neural network (CNN) models with a secret key set so that unauthorized users without the correct key set cannot access trained models.
Multi-color balance for color constancy
In this paper, we propose a novel multi-color balance adjustment for color constancy.
Piracy-Resistant DNN Watermarking by Block-Wise Image Transformation with Secret Key
In this paper, we propose a novel DNN watermarking method that utilizes a learnable image transformation method with a secret key.
Generation of Gradient-Preserving Images allowing HOG Feature Extraction
In this paper, we propose a method for generating visually protected images, referred to as gradient-preserving images.
Transfer Learning-Based Model Protection With Secret Key
Models with pre-trained weights are fine-tuned by using such transformed images.
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.
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.
Ensemble of Models Trained by Key-based Transformed Images for Adversarially Robust Defense Against Black-box Attacks
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.
A Privacy-Preserving Content-Based Image Retrieval Scheme Allowing Mixed Use Of Encrypted And Plain Images
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.
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.
Block-wise Image Transformation with Secret Key for Adversarially Robust Defense
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.
Extension of JPEG XS for Two-Layer 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.
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.
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.
Encryption Inspired Adversarial Defense for Visual Classification
The experiments are carried out on both adaptive and non-adaptive maximum-norm bounded white-box attacks while considering obfuscated gradients.
Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs
In an image-classification experiment with four CNNs: a simple CNN, VGG8, ResNet-18, and ResNet-101, applying the fixed layers to these CNNs is shown to improve the classification performance of all CNNs.
Privacy-Preserving Machine Learning Using EtC Images
In this paper, we propose a novel privacy-preserving machine learning scheme with encrypted images, called EtC (Encryption-then-Compression) images.
An Image Fusion Scheme for Single-Shot High Dynamic Range Imaging with Spatially Varying Exposures
This paper proposes a novel multi-exposure image fusion (MEF) scheme for single-shot high dynamic range imaging with spatially varying exposures (SVE).
Single-Shot High Dynamic Range Imaging with Spatially Varying Exposures Considering Hue Distortion
We proposes a novel single-shot high dynamic range imaging scheme with spatially varying exposures (SVE) considering hue distortion.
Adversarial Test on Learnable Image Encryption
Data for deep learning should be protected for privacy preserving.
Performance Evaluation of Two-layer lossless HDR Coding using Histogram Packing Technique under Various Tone-mapping Operators
We proposed a lossless two-layer HDR coding method using a histogram packing technique.
Two-layer Near-lossless HDR Coding with Backward Compatibility to JPEG
The experimental results indicate that the proposed method exhibits not only a better near-lossless compression performance than that of the two-layer coding method of the JPEG XT, but also there are no issue regarding the combination of parameter values without losing backward compatibility to the JPEG standard.
Convolutional Neural Networks Considering Local and Global features for Image Enhancement
To handle both local and global features, the proposed architecture consists of three networks: a local encoder, a global encoder, and a decoder.
HOG feature extraction from encrypted images for privacy-preserving machine learning
In this paper, we propose an extraction method of HOG (histograms-of-oriented-gradients) features from encryption-then-compression (EtC) images for privacy-preserving machine learning, where EtC images are images encrypted by a block-based encryption method proposed for EtC systems with JPEG compression, and HOG is a feature descriptor used in computer vision for the purpose of object detection and image classification.
JPEG XT Image Compression with Hue Compensation for Two-Layer HDR Coding
In order to suppress the color distortion, we apply a novel hue compensation method based on the maximally saturated colors.
A Noise-aware Enhancement Method for Underexposed Images
These methods, however, have two problems: (1) The loss of details in bright regions due to over-enhancement of contrast.
Multimedia
Image Enhancement Network Trained by Using HDR images
Most of conventional image enhancement methods, including Retinex based methods, do not take into account restoring lost pixel values caused by clipping and quantizing.
A Retinex-based Image Enhancement Scheme with Noise Aware Shadow-up Function
This paper proposes a novel image contrast enhancement method based on both a noise aware shadow-up function and Retinex (retina and cortex) decomposition.
Encryption-then-Compression Systems using Grayscale-based Image Encryption for JPEG Images
These features enhance security against various attacks such as jigsaw puzzle solver and brute-force attacks.
Cryptography and Security
Bitstream-Based JPEG Image Encryption with File-Size Preserving
An encryption scheme of JPEG images in the bitstream domain is proposed.
Two-Layer Lossless HDR Coding using Histogram Packing Technique with Backward Compatibility to JPEG
The experimental results demonstrate that not only the proposed method has a better lossless compression performance than that of the JPEG XT, but also there is no need to determine image-dependent parameter values for good compression performance without losing the backward compatibility to the well known legacy JPEG standard.
A Pseudo Multi-Exposure Fusion Method Using Single Image
The proposed method enables us to produce pseudo multi-exposure images from a single image.
Two-layer Lossless HDR Coding considering Histogram Sparseness with Backward Compatibility to JPEG
The experimental results demonstrate that not only the proposed method has a better lossless compression performance than that of the JPEG XT, but also there is no need to determine image-dependent parameter values for good compression performance in spite of having the backward compatibility to the well known legacy JPEG standard.
Multi-Exposure Image Fusion Based on Exposure Compensation
This paper proposes a novel multi-exposure image fusion method based on exposure compensation.
Super-Resolution using Convolutional Neural Networks without Any Checkerboard Artifacts
It is well-known that a number of excellent super-resolution (SR) methods using convolutional neural networks (CNNs) generate checkerboard artifacts.
Automatic Exposure Compensation for Multi-Exposure Image Fusion
In conventional works, it has been pointed out that the quality of those multi-exposure images can be improved by adjusting the luminance of them.
