arXiv subjects

Minoru Kuribayashi

Publications and source records attributed to Minoru Kuribayashi.

17 recordsLinked to original sources

arXiv2025

Ownership Verification of DNN Models Using White-Box Adversarial Attacks with Specified Probability Manipulation

In this paper, we propose a novel framework for ownership verification of deep neural network (DNN) models for image classification tasks. It allows verification of model identity by both the rightful owner and third party without presenting the original model. We assume a gray-box scenario where an unauthorized user owns a model that is illegally copied from the original model, provides services in a cloud environment, and the user throws images and receives the classification results as a probability distribution of output classes. The framework applies a white-box adversarial attack to align the output probability of a specific class to a designated value. Due to the knowledge of original model, it enables the owner to generate such adversarial examples. We propose a simple but effective adversarial attack method based on the iterative Fast Gradient Sign Method (FGSM) by introducing control parameters. Experimental results confirm the effectiveness of the identification of DNN models using adversarial attack.

cs.LG↗

arXiv2024

FreeMark: A Non-Invasive White-Box Watermarking for Deep Neural Networks

Deep neural networks (DNNs) have achieved significant success in real-world applications. However, safeguarding their intellectual property (IP) remains extremely challenging. Existing DNN watermarking for IP protection often require modifying DNN models, which reduces model performance and limits their practicality. This paper introduces FreeMark, a novel DNN watermarking framework that leverages cryptographic principles without altering the original host DNN model, thereby avoiding any reduction in model performance. Unlike traditional DNN watermarking methods, FreeMark innovatively generates secret keys from a pre-generated watermark vector and the host model using gradient descent. These secret keys, used to extract watermark from the model's activation values, are securely stored with a trusted third party, enabling reliable watermark extraction from suspect models. Extensive experiments demonstrate that FreeMark effectively resists various watermark removal attacks while maintaining high watermark capacity.

cs.CR↗

arXiv2024

EAViT: External Attention Vision Transformer for Audio Classification

This paper presents the External Attention Vision Transformer (EAViT) model, a novel approach designed to enhance audio classification accuracy. As digital audio resources proliferate, the demand for precise and efficient audio classification systems has intensified, driven by the need for improved recommendation systems and user personalization in various applications, including music streaming platforms and environmental sound recognition. Accurate audio classification is crucial for organizing vast audio libraries into coherent categories, enabling users to find and interact with their preferred audio content more effectively. In this study, we utilize the GTZAN dataset, which comprises 1,000 music excerpts spanning ten diverse genres. Each 30-second audio clip is segmented into 3-second excerpts to enhance dataset robustness and mitigate overfitting risks, allowing for more granular feature analysis. The EAViT model integrates multi-head external attention (MEA) mechanisms into the Vision Transformer (ViT) framework, effectively capturing long-range dependencies and potential correlations between samples. This external attention (EA) mechanism employs learnable memory units that enhance the network's capacity to process complex audio features efficiently. The study demonstrates that EAViT achieves a remarkable overall accuracy of 93.99%, surpassing state-of-the-art models.

cs.SD↗

arXiv2023

Image-Based Virtual Try-on System With Clothing-Size Adjustment

The conventional image-based virtual try-on method cannot generate fitting images that correspond to the clothing size because the system cannot accurately reflect the body information of a person. In this study, an image-based virtual try-on system that could adjust the clothing size was proposed. The size information of the person and clothing were used as the input for the proposed method to visualize the fitting of various clothing sizes in a virtual space. First, the distance between the shoulder width and height of the clothing in the person image is calculated based on the coordinate information of the key points detected by OpenPose. Then, the system changes the size of only the clothing area of the segmentation map, whose layout is estimated using the size of the person measured in the person image based on the ratio of the person and clothing sizes. If the size of the clothing area increases during the drawing, the details in the collar and overlapping areas are corrected to improve visual appearance.

cs.CV↗

arXiv2023

HDR image watermarking using saliency detection and quantization index modulation

High-dynamic range (HDR) images are circulated rapidly over the internet with risks of being exploited for unauthorized usage. To protect these images, some HDR image based watermarking (HDR-IW) methods were put forward. However, they inherited the same problem faced by conventional IW methods for standard dynamic range (SDR) images, where only trade-offs among conflicting requirements are managed instead of simultaneous improvement. In this paper, a novel saliency (eye-catching object) detection based trade-off independent HDR-IW is proposed, to simultaneously improve robustness, imperceptibility and payload. First, the host image goes through our proposed salient object detection model to produce a saliency map, which is, in turn, exploited to segment the foreground and background of the host image. Next, the binary watermark is partitioned into the foregrounds and backgrounds using the same mask and scrambled using a random permutation algorithm. Finally, the watermark segments are embedded into selected bit-plane of the corresponding host segments using quantized indexed modulation. Experimental results suggest that the proposed work outperforms state-of-the-art methods in terms of improving the conflicting requirements.

cs.CV↗

arXiv2022

Reversible Data Hiding in Encrypted Text Using Paillier Cryptosystem

Reversible Data Hiding in Encrypted Domain (RDHED) is an innovative method that can keep cover information secret and allows the data hider to insert additional information into it. This article presents a novel data hiding technique in an encrypted text called Reversible Data Hiding in Encrypted Text (RDHET). Initially, the original text is converted into their ASCII values. After that, the Paillier cryptosystem is adopted to encrypt all ASCII values of the original text and send it to the data hider for further processing. At the data hiding phase, the secret data are embedded into homomorphically encrypted text using a technique that does not lose any information, i.e., the homomorphic properties of the Paillier cryptosystem. Finally, the embedded secret data and the original text are recovered at the receiving end without any loss. Experimental results show that the proposed scheme is vital in the context of encrypted text processing at cloud-based services. Moreover, the scheme works well, especially for the embedding phase, text recovery, and performance on different security key sizes.

cs.CR↗

arXiv2022

A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals

Rolling bearings are the most crucial components of rotating machinery. Identifying defective bearings in a timely manner may prevent the malfunction of an entire machinery system. The mechanical condition monitoring field has entered the big data phase as a result of the fast advancement of machine parts. When working with large amounts of data, the manual feature extraction approach has the drawback of being inefficient and inaccurate. Data-driven methods like the Deep Learning method have been successfully used in recent years for mechanical intelligent fault detection. Convolutional neural networks (CNNs) were mostly used in earlier research to detect and identify bearing faults. The CNN model, however, suffers from the drawback of having trouble managing fault-time information, which results in a lack of classification results. In this study, bearing defects have been classified using a state-of-the-art Vision Transformer (ViT). Bearing defects were classified using Case Western Reserve University (CWRU) bearing failure laboratory experimental data. The research took into account 13 distinct kinds of defects under 0-load situations in addition to normal bearing conditions. Using the short-time Fourier transform (STFT), the vibration signals were converted into 2D time-frequency images. The 2D time-frequency images are used as input parameters for the ViT. The model achieved an overall accuracy of 98.8%.

cs.CV↗

arXiv2021

Immunization of Pruning Attack in DNN Watermarking Using Constant Weight Code

To ensure protection of the intellectual property rights of DNN models, watermarking techniques have been investigated to insert side-information into the models without seriously degrading the performance of original task. One of the threats for the DNN watermarking is the pruning attack such that less important neurons in the model are pruned to make it faster and more compact as well as to remove the watermark. In this study, we investigate a channel coding approach to resist the pruning attack. As the channel model is completely different from conventional models like digital images, it has been an open problem what kind of encoding method is suitable for DNN watermarking. A novel encoding approach by using constant weight codes to immunize the effects of pruning attacks is presented. To the best of our knowledge, this is the first study that introduces an encoding technique for DNN watermarking to make it robust against pruning attacks.

cs.CR↗

arXiv2019

Detecting and Correcting Adversarial Images Using Image Processing Operations

Deep neural networks (DNNs) have achieved excellent performance on several tasks and have been widely applied in both academia and industry. However, DNNs are vulnerable to adversarial machine learning attacks, in which noise is added to the input to change the network output. We have devised an image-processing-based method to detect adversarial images based on our observation that adversarial noise is reduced after applying these operations while the normal images almost remain unaffected. In addition to detection, this method can be used to restore the adversarial images' original labels, which is crucial to restoring the normal functionalities of DNN-based systems. Testing using an adversarial machine learning database we created for generating several types of attack using images from the ImageNet Large Scale Visual Recognition Challenge database demonstrated the efficiency of our proposed method for both detection and correction.

cs.LG↗

arXiv2019

Efficient and error-tolerant schemes for non-adaptive complex group testing and its application in complex disease genetics

The goal of combinatorial group testing is to efficiently identify up to $d$ defective items in a large population of $n$ items, where $d \ll n$. Defective items satisfy certain properties while the remaining items in the population do not. To efficiently identify defective items, a subset of items is pooled and then tested. In this work, we consider complex group testing (CmplxGT) in which a set of defective items consists of subsets of positive items (called \textit{positive complexes}). CmplxGT is classified into two categories: classical CmplxGT (CCmplxGT) and generalized CmplxGT (GCmplxGT). In CCmplxGT, the outcome of a test on a subset of items is positive if the subset contains at least one positive complex, and negative otherwise. In GCmplxGT, the outcome of a test on a subset of items is positive if the subset has a certain number of items of some positive complex, and negative otherwise. For CCmplxGT, we present a scheme that efficiently identifies all positive complexes in time $t \times \mathrm{poly}(d, \ln{n})$ in the presence of erroneous outcomes, where $t$ is a predefined parameter. As $d \ll n$, this is significantly better than the currently best time of $\mathrm{poly}(t) \times O(n \ln{n})$. Moreover, in specific cases, the number of tests in our proposed scheme is smaller than previous work. For GCmplxGT, we present a scheme that efficiently identifies all positive complexes. These schemes are directly applicable in various areas such as complex disease genetics, molecular biology, and learning a hidden graph.

cs.IT↗

arXiv2019

A framework for generalized group testing with inhibitors and its potential application in neuroscience

The main goal of group testing with inhibitors (GTI) is to efficiently identify a small number of defective items and inhibitor items in a large set of items. A test on a subset of items is positive if the subset satisfies some specific properties. Inhibitor items cancel the effects of defective items, which often make the outcome of a test containing defective items negative. Different GTI models can be formulated by considering how specific properties have different cancellation effects. This work introduces generalized GTI (GGTI) in which a new type of items is added, i.e., hybrid items. A hybrid item plays the roles of both defectives items and inhibitor items. Since the number of instances of GGTI is large (more than 7 million), we introduce a framework for classifying all types of items non-adaptively, i.e., all tests are designed in advance. We then explain how GGTI can be used to classify neurons in neuroscience. Finally, we show how to realize our proposed scheme in practice.

cs.IT↗

arXiv2019

Sublinear decoding schemes for non-adaptive group testing with inhibitors

Identification of up to $d$ defective items and up to $h$ inhibitors in a set of $n$ items is the main task of non-adaptive group testing with inhibitors. To efficiently reduce the cost of this Herculean task, a subset of the $n$ items is formed and then tested. This is called \textit{group testing}. A test outcome on a subset of items is positive if the subset contains at least one defective item and no inhibitors, and negative otherwise. We present two decoding schemes for efficiently identifying the defective items and the inhibitors in the presence of $e$ erroneous outcomes in time $\mathsf{poly}(d, h, e, \log_2{n})$, which is sublinear to the number of items $n$. This decoding complexity significantly improves the state-of-the-art schemes in which the decoding time is linear to the number of items $n$, i.e., $\mathsf{poly}(d, h, e, n)$. Moreover, each column of the measurement matrices associated with the proposed schemes can be nonrandomly generated in polynomial order of the number of rows. As a result, one can save space for storing them. Simulation results confirm our theoretical analysis. When the number of items is sufficiently large, the decoding time in our proposed scheme is smallest in comparison with existing work. In addition, when some erroneous outcomes are allowed, the number of tests in the proposed scheme is often smaller than the number of tests in existing work.

cs.IT↗

arXiv2019

Improved encoding and decoding for non-adaptive threshold group testing

The goal of threshold group testing is to identify up to $d$ defective items among a population of $n$ items, where $d$ is usually much smaller than $n$. A test is positive if it has at least $u$ defective items and negative otherwise. Our objective is to identify defective items in sublinear time the number of items, e.g., $\mathrm{poly}(d, \ln{n}),$ by using the number of tests as low as possible. In this paper, we reduce the number of tests to $O \left( h \times \frac{d^2 \ln^2{n}}{\mathsf{W}^2(d \ln{n})} \right)$ and the decoding time to $O \left( \mathrm{dec}_0 \times h \right),$ where $\\mathrm{dec}_0 = O \left( \frac{d^{3.57} \ln^{6.26}{n}}{\mathsf{W}^{6.26}(d \ln{n})} \right) + O \left( \frac{d^6 \ln^4{n}}{\mathsf{W}^4(d \ln{n})} \right)$, $h = O\left( \frac{d_0^2 \ln{\frac{n}{d_0}}}{(1-p)^2} \right)$ , $d_0 = \max\{u, d - u \}$, $p \in [0, 1),$ and $\mathsf{W}(x) = Θ\left( \ln{x} - \ln{\ln{x}} \right).$ If the number of tests is increased to $O\left( h \times \frac{d^2\ln^3{n}}{\mathsf{W}^2(d \ln{n})} \right),$ the decoding complexity is reduced to $O \left(\mathrm{dec}_1 \times h \right),$ where $\mathrm{dec}_1 = \max \left\{ \frac{d^2 \ln^3{n}}{\mathsf{W}^2(d \ln{n})}, \frac{ud \ln^4{n}}{\mathsf{W}^3(d \ln{n})} \right\}.$ Moreover, our proposed scheme is capable of handling errors in test outcomes.

cs.IT↗

arXiv2018

Efficient (nonrandom) construction and decoding for non-adaptive group testing

The task of non-adaptive group testing is to identify up to $d$ defective items from $N$ items, where a test is positive if it contains at least one defective item, and negative otherwise. If there are $t$ tests, they can be represented as a $t \times N$ measurement matrix. We have answered the question of whether there exists a scheme such that a larger measurement matrix, built from a given $t\times N$ measurement matrix, can be used to identify up to $d$ defective items in time $O(t \log_2{N})$. In the meantime, a $t \times N$ nonrandom measurement matrix with $t = O \left(\frac{d^2 \log_2^2{N}}{(\log_2(d\log_2{N}) - \log_2{\log_2(d\log_2{N})})^2} \right)$ can be obtained to identify up to $d$ defective items in time $\mathrm{poly}(t)$. This is much better than the best well-known bound, $t = O \left( d^2 \log_2^2{N} \right)$. For the special case $d = 2$, there exists an efficient nonrandom construction in which at most two defective items can be identified in time $4\log_2^2{N}$ using $t = 4\log_2^2{N}$ tests. Numerical results show that our proposed scheme is more practical than existing ones, and experimental results confirm our theoretical analysis. In particular, up to $2^{7} = 128$ defective items can be identified in less than $16$s even for $N = 2^{100}$.

cs.IT↗

arXiv2018

Efficiently Decodable Non-Adaptive Threshold Group Testing

We consider non-adaptive threshold group testing for identification of up to $d$ defective items in a set of $n$ items, where a test is positive if it contains at least $2 \leq u \leq d$ defective items, and negative otherwise. The defective items can be identified using $t = O \left( \left( \frac{d}{u} \right)^u \left( \frac{d}{d - u} \right)^{d-u} \left(u \log{\frac{d}{u}} + \log{\frac{1}ε} \right) \cdot d^2 \log{n} \right)$ tests with probability at least $1 - ε$ for any $ε> 0$ or $t = O \left( \left( \frac{d}{u} \right)^u \left( \frac{d}{d -u} \right)^{d - u} d^3 \log{n} \cdot \log{\frac{n}{d}} \right)$ tests with probability 1. The decoding time is $t \times \mathrm{poly}(d^2 \log{n})$. This result significantly improves the best known results for decoding non-adaptive threshold group testing: $O(n\log{n} + n \log{\frac{1}ε})$ for probabilistic decoding, where $ε> 0$, and $O(n^u \log{n})$ for deterministic decoding.

cs.IT↗

arXiv2018

Efficient Decoding Schemes for Noisy Non-Adaptive Group Testing when Noise Depends on Number of Items in Test

The goal of non-adaptive group testing is to identify at most $d$ defective items from $N$ items, in which a test of a subset of $N$ items is positive if it contains at least one defective item, and negative otherwise. However, in many cases, especially in biological screening, the outcome is unreliable due to biochemical interaction; i.e., \textit{noise.} Consequently, a positive result can change to a negative one (false negative) and vice versa (false positive). In this work, we first consider the dilution effect in which \textit{the degree of noise depends on the number of items in the test}. Two efficient schemes are presented for identifying the defective items in time linearly to the number of tests needed. Experimental results validate our theoretical analysis. Specifically, setting the error precision of 0.001 and $d\leq16$, our proposed algorithms always identify all defective items in less than 7 seconds for $N=2^{33}\approx 9$ billion.

cs.IT↗

arXiv2017

Non-Adaptive Group Testing Framework based on Concatenation Code

We consider an efficiently decodable non-adaptive group testing (NAGT) problem that meets theoretical bounds. The problem is to find a few specific items (at most $d$) satisfying certain characteristics in a colossal number of $N$ items as quickly as possible. Those $d$ specific items are called \textit{defective items}. The idea of NAGT is to pool a group of items, which is called \textit{a test}, then run a test on them. If the test outcome is \textit{positive}, there exists at least one defective item in the test, and if it is \textit{negative}, there exists no defective items. Formally, a binary $t \times N$ measurement matrix $\mathcal{M} = (m_{ij})$ is the representation for $t$ tests where row $i$ stands for test $i$ and $m_{ij} = 1$ if and only if item $j$ belongs to test $i$. There are three main objectives in NAGT: minimize the number of tests $t$, construct matrix $\mathcal{M}$, and identify defective items as quickly as possible. In this paper, we present a strongly explicit construction of $\mathcal{M}$ for when the number of defective items is at most 2, with the number of tests $t \simeq 16 \log{N} = O(\log{N})$. In particular, we need only $K \simeq N \times 16\log{N} = O(N\log{N})$ bits to construct such matrices, which is optimal. Furthermore, given these $K$ bits, any entry in the matrix can be constructed in time $O \left(\ln{N}/ \ln{\ln{N}} \right)$. Moreover, $\mathcal{M}$ can be decoded with high probability in time $O\left( \frac{\ln^2{N}}{\ln^2{\ln{N}}} \right)$. When the number of defective items is greater than 2, we present a scheme that can identify at least $(1-ε)d$ defective items with $t \simeq 32 C(ε) d \log{N} = O(d \log{N})$ in time $O \left( d \frac{\ln^2{N}}{\ln^2{\ln{N}}} \right)$ for any close-to-zero $ε$, where $C(ε)$ is a constant that depends only on $ε$.

cs.IT↗