arXiv subjects

Hiroki Ito

Publications and source records attributed to Hiroki Ito.

11 recordsLinked to original sources

arXiv2022

Access Control with Encrypted Feature Maps for Object Detection Models

In this paper, we propose an access control method with a secret key for object detection models for the first time so that unauthorized users without a secret key cannot benefit from the performance of trained models. The method enables us not only to provide a high detection performance to authorized users but to also degrade the performance for unauthorized users. The use of transformed images was proposed for the access control of image classification models, but these images cannot be used for object detection models due to performance degradation. Accordingly, in this paper, selected feature maps are encrypted with a secret key for training and testing models, instead of input images. 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.

cs.CV↗

arXiv2022

Twisted intersection colorings, invariants and double coverings of twisted links

Twisted links are a generalization of classical links and correspond to stably equivalence classes of links in thickened surfaces. In this paper we introduce twisted intersection colorings of a diagram and construct two invariants of a twisted link using such colorings. As an application, we show that there exist infinitely many pairs of twisted links such that for each pair the two twisted links are not equivalent but their double coverings are equivalent. We also introduce a method of constructing a pair of twisted links whose double coverings are equivalent.

math.GT↗

arXiv2022

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. The method enables us not only to provide a high segmentation performance to authorized users but to also degrade the performance for unauthorized users. We first point out that, for the application of semantic segmentation, conventional access control methods which use encrypted images for classification tasks are not directly applicable due to performance degradation. Accordingly, in this paper, selected feature maps are encrypted with a secret key for training and testing models, instead of input images. 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.

cs.CV↗

arXiv2022

Superconductivity of Carbon Compounds with Sodalite Structure

We investigate the superconductivity of carbon compounds with a sodalite structure, which are similar to hydrogen compounds showing the high-temperature superconductivity. A systematic analysis by first-principles calculations is carried out, including examination of mechanical and dynamic instabilities under external pressure $P$. These instabilities are classified on the phase diagram for the effective doping charge versus the lattice constant of the system. We also present the superconducting transition temperature $T_{\rm c}$ as a function of $P$ for many carbon compounds and a pure carbon system with the sodalite structure. Some of them have $T_{\rm c}$ of up to about 100 K at $P > \sim 30$ GPa, and the results suggest that the sodalite structure of carbon may be a key to producing phonon-mediated high-$T_{\rm c}$ superconductivity.

cond-mat.supr-con↗

arXiv2022

Access Control of Object Detection Models Using Encrypted Feature Maps

In this paper, we propose an access control method for object detection models. The use of encrypted images or encrypted feature maps has been demonstrated to be effective in access control of models from unauthorized access. However, the effectiveness of the approach has been confirmed in only image classification models and semantic segmentation models, but not in object detection models. 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.

cs.CV↗

arXiv2021

Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Models

In this paper, we propose an access control method that uses the spatially invariant permutation of feature maps with a secret key for protecting semantic segmentation models. Segmentation models are trained and tested by permuting selected feature maps with a secret key. The proposed method allows rightful users with the correct key not only to access a model to full capacity but also to degrade the performance for unauthorized users. Conventional access control methods have focused only on image classification tasks, and these methods have never been applied to semantic segmentation tasks. 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. In addition, a conventional method with block-wise transformations was also verified to have degraded performance under semantic segmentation models.

cs.CV↗

arXiv2021

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. However, conventional model protection methods focused only the image classification task, and these protection methods were never applied to semantic segmentation although it has an increasing number of applications. In this paper, we propose to protect semantic segmentation models from unauthorized access by utilizing block-wise transformation with a secret key for the first time. Protected models are trained by using transformed images. Experiment results show that the proposed protection method allows rightful users with the correct key to access the model to full capacity and deteriorate the performance for unauthorized users. However, protected models slightly drop the segmentation performance compared to non-protected models.

eess.IV↗

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↗

arXiv2017

On the classification of $\mathbb{Z}_4$-codes

In this note, we study the classification of $\mathbb{Z}_4$-codes. For some special cases $(k_1,k_2)$, by hand, we give a classification of $\mathbb{Z}_4$-codes of length $n$ and type $4^{k_1}2^{k_2}$ satisfying a certain condition. Our exhaustive computer search completes the classification of $\mathbb{Z}_4$-codes of lengths up to $7$.

math.CO↗

arXiv2015

A remark on a priori estimate for the Navier-Stokes equations with the Coriolis force

The Cauchy problem for the Navier-Stokes equations with the Coriolis force is considered. It is proved that a similar a priori estimate, which is derived for the Navier-Stokes equations by Lei and Lin [11], holds under the effect of the Coriolis force. As an application existence of a unique global solution for arbitrary speed of rotation is proved, as well as its asymptotic behavior.

math.AP↗

arXiv2013

Classification of involutions on Enriques surfaces

We present the classification of involutions on Enriques surfaces. We classify those into 18 types with the help of the lattice theory due to Nikulin. We also give all examples of the classification.

math.AG↗