Searcharxiv⌕ Search

arXiv subjects

Isao Echizen

Publications and source records attributed to Isao Echizen.

At least 109 records · Page 6Linked to original sources

Improved non-adaptive algorithms for threshold group testing with a gap

The basic 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 $n$. The outcome of a test on a subset of items is positive if the subset has at least $u$ defective items, negative if it has up to $\ell$ defective items, where $0\leq\ell 0$, i.e., threshold group testing with a gap. Note that the results presented here are also applicable to the case $g = 0$; however, the results are not as efficient as those in related work. Currently, a few reported studies have investigated test designs and decoding algorithms for identifying defective items. Most of the previous studies have not been feasible because there are numerous constraints on their problem settings or the decoding complexities of their proposed schemes are relatively large. Therefore, it is compulsory to reduce the number of tests as well as the decoding complexity, i.e., the time for identifying the defective items, for achieving practical schemes. The work presented here makes five contributions. The first is a more accurate theorem for a non-adaptive algorithm for threshold group testing proposed by Chen and Fu. The second is an improvement in the construction of disjunct matrices, which are the main tools for tackling (threshold) group testing and other tasks such as constructing cover-free families or learning hidden graphs. The third and fourth contributions are a reduced exact upper bound on the number of tests and a reduced asymptotic bound on the decoding time for identifying defective items in a noisy setting on test outcomes. The fifth contribution is a simulation on the number of tests of the resulting improvements for previous work and the proposed theorems.

cs.IT↗

OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wild

The proliferation of deepfake media is raising concerns among the public and relevant authorities. It has become essential to develop countermeasures against forged faces in social media. This paper presents a comprehensive study on two new countermeasure tasks: multi-face forgery detection and segmentation in-the-wild. Localizing forged faces among multiple human faces in unrestricted natural scenes is far more challenging than the traditional deepfake recognition task. To promote these new tasks, we have created the first large-scale dataset posing a high level of challenges that is designed with face-wise rich annotations explicitly for face forgery detection and segmentation, namely OpenForensics. With its rich annotations, our OpenForensics dataset has great potentials for research in both deepfake prevention and general human face detection. We have also developed a suite of benchmarks for these tasks by conducting an extensive evaluation of state-of-the-art instance detection and segmentation methods on our newly constructed dataset in various scenarios. The dataset, benchmark results, codes, and supplementary materials will be publicly available on our project page: https://sites.google.com/view/ltnghia/research/openforensics

cs.CV↗

Fashion-Guided Adversarial Attack on Person Segmentation

This paper presents the first adversarial example based method for attacking human instance segmentation networks, namely person segmentation networks in short, which are harder to fool than classification networks. We propose a novel Fashion-Guided Adversarial Attack (FashionAdv) framework to automatically identify attackable regions in the target image to minimize the effect on image quality. It generates adversarial textures learned from fashion style images and then overlays them on the clothing regions in the original image to make all persons in the image invisible to person segmentation networks. The synthesized adversarial textures are inconspicuous and appear natural to the human eye. The effectiveness of the proposed method is enhanced by robustness training and by jointly attacking multiple components of the target network. Extensive experiments demonstrated the effectiveness of FashionAdv in terms of robustness to image manipulations and storage in cyberspace as well as appearing natural to the human eye. The code and data are publicly released on our project page https://github.com/nii-yamagishilab/fashion_adv

cs.CV↗

Viable Threat on News Reading: Generating Biased News Using Natural Language Models

Recent advancements in natural language generation has raised serious concerns. High-performance language models are widely used for language generation tasks because they are able to produce fluent and meaningful sentences. These models are already being used to create fake news. They can also be exploited to generate biased news, which can then be used to attack news aggregators to change their reader's behavior and influence their bias. In this paper, we use a threat model to demonstrate that the publicly available language models can reliably generate biased news content based on an input original news. We also show that a large number of high-quality biased news articles can be generated using controllable text generation. A subjective evaluation with 80 participants demonstrated that the generated biased news is generally fluent, and a bias evaluation with 24 participants demonstrated that the bias (left or right) is usually evident in the generated articles and can be easily identified.

cs.CL↗

Generating Master Faces for Use in Performing Wolf Attacks on Face Recognition Systems

Due to its convenience, biometric authentication, especial face authentication, has become increasingly mainstream and thus is now a prime target for attackers. Presentation attacks and face morphing are typical types of attack. Previous research has shown that finger-vein- and fingerprint-based authentication methods are susceptible to wolf attacks, in which a wolf sample matches many enrolled user templates. In this work, we demonstrated that wolf (generic) faces, which we call "master faces," can also compromise face recognition systems and that the master face concept can be generalized in some cases. Motivated by recent similar work in the fingerprint domain, we generated high-quality master faces by using the state-of-the-art face generator StyleGAN in a process called latent variable evolution. Experiments demonstrated that even attackers with limited resources using only pre-trained models available on the Internet can initiate master face attacks. The results, in addition to demonstrating performance from the attacker's point of view, can also be used to clarify and improve the performance of face recognition systems and harden face authentication systems.

cs.CV↗

Security of Facial Forensics Models Against Adversarial Attacks

Deep neural networks (DNNs) have been used in digital forensics to identify fake facial images. We investigated several DNN-based forgery forensics models (FFMs) to examine whether they are secure against adversarial attacks. We experimentally demonstrated the existence of individual adversarial perturbations (IAPs) and universal adversarial perturbations (UAPs) that can lead a well-performed FFM to misbehave. Based on iterative procedure, gradient information is used to generate two kinds of IAPs that can be used to fabricate classification and segmentation outputs. In contrast, UAPs are generated on the basis of over-firing. We designed a new objective function that encourages neurons to over-fire, which makes UAP generation feasible even without using training data. Experiments demonstrated the transferability of UAPs across unseen datasets and unseen FFMs. Moreover, we conducted subjective assessment for imperceptibility of the adversarial perturbations, revealing that the crafted UAPs are visually negligible. These findings provide a baseline for evaluating the adversarial security of FFMs.

cs.CV↗

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↗

Generating Sentiment-Preserving Fake Online Reviews Using Neural Language Models and Their Human- and Machine-based Detection

Advanced neural language models (NLMs) are widely used in sequence generation tasks because they are able to produce fluent and meaningful sentences. They can also be used to generate fake reviews, which can then be used to attack online review systems and influence the buying decisions of online shoppers. To perform such attacks, it is necessary for experts to train a tailored LM for a specific topic. In this work, we show that a low-skilled threat model can be built just by combining publicly available LMs and show that the produced fake reviews can fool both humans and machines. In particular, we use the GPT-2 NLM to generate a large number of high-quality reviews based on a review with the desired sentiment and then using a BERT based text classifier (with accuracy of 96%) to filter out reviews with undesired sentiments. Because none of the words in the review are modified, fluent samples like the training data can be generated from the learned distribution. A subjective evaluation with 80 participants demonstrated that this simple method can produce reviews that are as fluent as those written by people. It also showed that the participants tended to distinguish fake reviews randomly. Three countermeasures, Grover, GLTR, and OpenAI GPT-2 detector, were found to be difficult to accurately detect fake review.

cs.CL↗

A Method for Identifying Origin of Digital Images Using a Convolution Neural Network

The rapid development of deep learning techniques has created new challenges in identifying the origin of digital images because generative adversarial networks and variational autoencoders can create plausible digital images whose contents are not present in natural scenes. In this paper, we consider the origin that can be broken down into three categories: natural photographic image (NPI), computer generated graphic (CGG), and deep network generated image (DGI). A method is presented for effectively identifying the origin of digital images that is based on a convolutional neural network (CNN) and uses a local-to-global framework to reduce training complexity. By feeding labeled data, the CNN is trained to predict the origin of local patches cropped from an image. The origin of the full-size image is then determined by majority voting. Unlike previous forensic methods, the CNN takes the raw pixels as input without the aid of "residual map". Experimental results revealed that not only the high-frequency components but also the middle-frequency ones contribute to origin identification. The proposed method achieved up to 95.21% identification accuracy and behaved robustly against several common post-processing operations including JPEG compression, scaling, geometric transformation, and contrast stretching. The quantitative results demonstrate that the proposed method is more effective than handcrafted feature-based methods.

cs.CV↗

Use of a Capsule Network to Detect Fake Images and Videos

The revolution in computer hardware, especially in graphics processing units and tensor processing units, has enabled significant advances in computer graphics and artificial intelligence algorithms. In addition to their many beneficial applications in daily life and business, computer-generated/manipulated images and videos can be used for malicious purposes that violate security systems, privacy, and social trust. The deepfake phenomenon and its variations enable a normal user to use his or her personal computer to easily create fake videos of anybody from a short real online video. Several countermeasures have been introduced to deal with attacks using such videos. However, most of them are targeted at certain domains and are ineffective when applied to other domains or new attacks. In this paper, we introduce a capsule network that can detect various kinds of attacks, from presentation attacks using printed images and replayed videos to attacks using fake videos created using deep learning. It uses many fewer parameters than traditional convolutional neural networks with similar performance. Moreover, we explain, for the first time ever in the literature, the theory behind the application of capsule networks to the forensics problem through detailed analysis and visualization.

cs.CV↗

Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videos

Detecting manipulated images and videos is an important topic in digital media forensics. Most detection methods use binary classification to determine the probability of a query being manipulated. Another important topic is locating manipulated regions (i.e., performing segmentation), which are mostly created by three commonly used attacks: removal, copy-move, and splicing. We have designed a convolutional neural network that uses the multi-task learning approach to simultaneously detect manipulated images and videos and locate the manipulated regions for each query. Information gained by performing one task is shared with the other task and thereby enhance the performance of both tasks. A semi-supervised learning approach is used to improve the network's generability. The network includes an encoder and a Y-shaped decoder. Activation of the encoded features is used for the binary classification. The output of one branch of the decoder is used for segmenting the manipulated regions while that of the other branch is used for reconstructing the input, which helps improve overall performance. Experiments using the FaceForensics and FaceForensics++ databases demonstrated the network's effectiveness against facial reenactment attacks and face swapping attacks as well as its ability to deal with the mismatch condition for previously seen attacks. Moreover, fine-tuning using just a small amount of data enables the network to deal with unseen attacks.

cs.CV↗

Speaker Anonymization Using X-vector and Neural Waveform Models

The social media revolution has produced a plethora of web services to which users can easily upload and share multimedia documents. Despite the popularity and convenience of such services, the sharing of such inherently personal data, including speech data, raises obvious security and privacy concerns. In particular, a user's speech data may be acquired and used with speech synthesis systems to produce high-quality speech utterances which reflect the same user's speaker identity. These utterances may then be used to attack speaker verification systems. One solution to mitigate these concerns involves the concealing of speaker identities before the sharing of speech data. For this purpose, we present a new approach to speaker anonymization. The idea is to extract linguistic and speaker identity features from an utterance and then to use these with neural acoustic and waveform models to synthesize anonymized speech. The original speaker identity, in the form of timbre, is suppressed and replaced with that of an anonymous pseudo identity. The approach exploits state-of-the-art x-vector speaker representations. These are used to derive anonymized pseudo speaker identities through the combination of multiple, random speaker x-vectors. Experimental results show that the proposed approach is effective in concealing speaker identities. It increases the equal error rate of a speaker verification system while maintaining high quality, anonymized speech.

eess.AS↗

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↗

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↗

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↗

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↗

Identifying Computer-Translated Paragraphs using Coherence Features

We have developed a method for extracting the coherence features from a paragraph by matching similar words in its sentences. We conducted an experiment with a parallel German corpus containing 2000 human-created and 2000 machine-translated paragraphs. The result showed that our method achieved the best performance (accuracy = 72.3%, equal error rate = 29.8%) when it is compared with previous methods on various computer-generated text including translation and paper generation (best accuracy = 67.9%, equal error rate = 32.0%). Experiments on Dutch, another rich resource language, and a low resource one (Japanese) attained similar performances. It demonstrated the efficiency of the coherence features at distinguishing computer-translated from human-created paragraphs on diverse languages.

cs.CL↗

Audiovisual speaker conversion: jointly and simultaneously transforming facial expression and acoustic characteristics

An audiovisual speaker conversion method is presented for simultaneously transforming the facial expressions and voice of a source speaker into those of a target speaker. Transforming the facial and acoustic features together makes it possible for the converted voice and facial expressions to be highly correlated and for the generated target speaker to appear and sound natural. It uses three neural networks: a conversion network that fuses and transforms the facial and acoustic features, a waveform generation network that produces the waveform from both the converted facial and acoustic features, and an image reconstruction network that outputs an RGB facial image also based on both the converted features. The results of experiments using an emotional audiovisual database showed that the proposed method achieved significantly higher naturalness compared with one that separately transformed acoustic and facial features.

eess.AS↗