To protect user privacy and establish self-information control rights, service providers must notify users of their privacy policies and obtain their consent in advance. The frameworks that impose these requirements are mandatory. Although originally designed to protect user privacy, obtaining user consent in advance has become a mere formality. These problems are induced by the gap between service providers' privacy policies, which prioritize the observance of laws and guidelines, and user expectations which are to easily understand how their data will be handled. To reduce this gap, we construct a tool supporting users in reading privacy policies in Japanese. We designed the tool to present users with separate unique expressions containing relevant information to improve the display format of the privacy policy and render it more comprehensive for Japanese users. To accurately extract the unique expressions from privacy policies, we created training data for machine learning for the constructed tool. The constructed tool provides a summary of privacy policies for users to help them understand the policies of interest. Subsequently, we assess the effectiveness of the constructed tool in experiments and follow-up questionnaires. Our findings reveal that the constructed tool enhances the users' subjective understanding of the services they read about and their awareness of the related risks. We expect that the developed tool will help users better understand the privacy policy content and and make educated decisions based on their understanding of how service providers intend to use their personal data.

Companies listed on the stock exchange are required to share their annual reports with the U.S. Securities and Exchange Commission (SEC) within the first three months following the fiscal year. These reports, namely 10-K Filings, are presented to public interest by the SEC through an Electronic Data Gathering, Analysis, and Retrieval database. 10-K Filings use standard file formats (xbrl, html, pdf) to publish the financial reports of the companies. Although the file formats propose a standard structure, the content and the meta-data of the financial reports (e.g. tag names) is not strictly bound to a pre-defined schema. This study proposes a data collection and data preprocessing method to semantify the financial reports and use the collected data for further analysis (i.e. machine learning). The analysis of eight different datasets, which were created during the study, are presented using the proposed data transformation methods. As a use case, based on the datasets, five different machine learning algorithms were utilized to predict the existence of the corresponding company in the S&P 500 index. According to the strong machine learning results, the dataset generation methodology is successful and the datasets are ready for further use.

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%.

Multiple wireless communication systems are often operated together in the same area in such manufacturing sites as factories where wideband noise may be emitted from industrial equipment over channels for wireless communication systems. To perform highly reliable wireless communication in such environments, radio wave environments must be monitored that are specific to each manufacturing site to find channels and timing that enable stable communication. The authors studied technologies using machine learning to efficiently analyze a large amount of monitoring data, including signals whose spectrum shape is undefined, such as electromagnetic noise over a wideband. In this paper, we generated common supervised data for multiple sensors by conjointly clustering features after normalizing those calculated in each sensor to recognize the signal reception timing from identical sources and eliminate the complexity of supervised data management. We confirmed our method's effectiveness through signal models and actual data sampled by sensors that we developed.

This paper focuses on the potential value and future prospects of using virtual reality (VR) technology in online education. In detailing online education and the latest VR technology, we focus on metaverse construction and artificial intelligence (AI) for educational VR use. In particular, we describe a virtual university campus in which on-demand VR lectures are conducted in virtual lecture halls, automated evaluations of student learning and training using machine learning, and the linking of multiple digital campuses.

With the continued innovation of deep neural networks, spiking neural networks (SNNs) that more closely resemble biological brain synapses have attracted attention because of their low power consumption. Unlike artificial neural networks (ANNs), for continuous data values, they must employ an encoding process to convert the values to spike trains, suppressing the SNN's performance. To avoid this degradation, the incoming analog signal must be regulated prior to the encoding process, which is also realized in living things eg, the basement membranes of humans mechanically perform the Fourier transform. To this end, we combine an ANN and an SNN to build ANN-to-SNN hybrid neural networks (HNNs) that improve the concerned performance. To qualify this performance and robustness, MNIST and CIFAR-10 image datasets are used for various classification tasks in which the training and encoding methods changes. In addition, we present simultaneous and separate training methods for the artificial and spiking layers, considering the encoding methods of each. We find that increasing the number of artificial layers at the expense of spiking layers improves the HNN performance. For straightforward datasets such as MNIST, similar performances as ANN's are achieved by using duplicate coding and separate learning. However, for more complex tasks, the use of Gaussian coding and simultaneous learning is found to improve the accuracy of the HNN while lower power consumption.

Mobile communication systems are not only the core of the Information and Communication Technology (ICT) infrastructure but also that of our social infrastructure. The 5th generation mobile communication system (5G) has already started and is in use. 5G is expected for various use cases in industry and society. Thus, many companies and research institutes are now trying to improve the performance of 5G, that is, 5G Enhancement and the next generation of mobile communication systems (Beyond 5G (6G)). 6G is expected to meet various highly demanding requirements even compared with 5G, such as extremely high data rate, extremely large coverage, extremely low latency, extremely low energy, extremely high reliability, extreme massive connectivity, and so on. Artificial intelligence (AI) and machine learning (ML), AI/ML, will have more important roles than ever in 6G wireless communications with the above extreme high requirements for a diversity of applications, including new combinations of the requirements for new use cases. We can say that AI/ML will be essential for 6G wireless communications. This paper introduces some ML techniques and applications in 6G wireless communications, mainly focusing on the physical layer.

Deep neural networks (DNNs) perform well for image recognition, speech recognition, and pattern analysis. However, such neural networks are vulnerable to adversarial examples. An adversarial example is a data sample created by adding a small amount of noise to an original sample in such a way that it is difficult for humans to identify but that will cause the sample to be misclassified by a target model. In a military environment, adversarial examples that are correctly classified by a friendly model while deceiving an enemy model may be useful. In this paper, we propose a method for generating a selective adversarial example that is correctly classified by a friendly gait recognition system and misclassified by an enemy gait recognition system. The proposed scheme generates the selective adversarial example by combining the loss for correct classification by the friendly gait recognition system with the loss for misclassification by the enemy gait recognition system. In our experiments, we used the CASIA Gait Database as the dataset and TensorFlow as the machine learning library. The results show that the proposed method can generate selective adversarial examples that have a 98.5% attack success rate against an enemy gait recognition system and are classified with 87.3% accuracy by a friendly gait recognition system.

This paper focuses on the “data collection period” for training a better Just-In-Time (JIT) defect prediction model — the early commit data vs. the recent one —, and conducts a large-scale comparative study to explore an appropriate data collection period. Since there are many possible machine learning algorithms for training defect prediction models, the selection of machine learning algorithms can become a threat to validity. Hence, this study adopts the automatic machine learning method to mitigate the selection bias in the comparative study. The empirical results using 122 open-source software projects prove the trend that the dataset composed of the recent commits would become a better training set for JIT defect prediction models.

Monocular depth estimation has improved drastically due to the development of deep neural networks (DNNs). However, recent studies have revealed that DNNs for monocular depth estimation contain vulnerabilities that can lead to misestimation when perturbations are added to input. This study investigates whether DNNs for monocular depth estimation is vulnerable to misestimation when patterned light is projected on an object using a video projector. To this end, this study proposes an evolutionary adversarial attack method with multi-fidelity evaluation scheme that allows creating adversarial examples under black-box condition while suppressing the computational cost. Experiments in both simulated and real scenes showed that the designed light pattern caused a DNN to misestimate objects as if they have moved to the back.

Multilayer perceptron (MLP) is a basic neural network model that is used in practical industrial applications, such as network intrusion detection (NID) systems. It is also used as a building block in newer models, such as gMLP. Currently, there is a demand for fast training in NID and other areas. However, in training with numerous GPUs, the problems of power consumption and long training times arise. Many of the latest deep neural network (DNN) models and MLPs are trained using a backpropagation algorithm which transmits an error gradient from the output layer to the input layer such that in the sequential computation, the next input cannot be processed until the weights of all layers are updated from the last layer. This is known as backward locking. In this study, a weight parameter update mechanism is proposed with time delays that can accommodate the weight update delay to allow simultaneous forward and backward computation. To this end, a one-dimensional systolic array structure was designed on a Xilinx U50 Alveo FPGA card in which each layer of the MLP is assigned to a processing element (PE). The time-delay backpropagation algorithm executes all layers in parallel, and transfers data between layers in a pipeline. Compared to the Intel Core i9 CPU and NVIDIA RTX 3090 GPU, it is 3 times faster than the CPU and 2.5 times faster than the GPU. The processing speed per power consumption is 11.5 times better than that of the CPU and 21.4 times better than that of the GPU. From these results, it is concluded that a training accelerator on an FPGA can achieve high speed and energy efficiency.

Deep neural networks show good performance in image recognition, speech recognition, and pattern analysis. However, deep neural networks also have weaknesses, one of which is vulnerability to poisoning attacks. A poisoning attack reduces the accuracy of a model by training the model on malicious data. A number of studies have been conducted on such poisoning attacks. The existing type of poisoning attack causes misrecognition by one classifier. In certain situations, however, it is necessary for multiple models to misrecognize certain data as different specific classes. For example, if there are enemy autonomous vehicles A, B, and C, a poisoning attack could mislead A to turn to the left, B to stop, and C to turn to the right simply by using a traffic sign. In this paper, we propose a multi-targeted poisoning attack method that causes each of several models to misrecognize certain data as a different target class. This study used MNIST and CIFAR10 as datasets and Tensorflow as a machine learning library. The experimental results show that the proposed scheme has a 100% average attack success rate on MNIST and CIFAR10 when malicious data accounting for 5% of the training dataset have been used for training.

In this paper, we propose a selective membership inference attack method that determines whether certain data corresponding to a specific class are being used as training data for a machine learning model or not. By using the proposed method, membership or non-membership can be inferred by generating a decision model from the prediction of the inference models and training the confidence values for the data corresponding to the selected class. We used MNIST as an experimental dataset and Tensorflow as a machine learning library. Experimental results show that the proposed method has a 92.4% success rate with 5 inference models for data corresponding to a specific class.

This paper presents a channel operating margin (COM) based high-speed serial link optimization using machine learning (ML). COM that is proposed for evaluating serial link is calculated at first and during the calculation several important equalization parameters corresponding to the best configuration are extracted which can be used for the ML modeling of serial link. Then a deep neural network containing hidden layers are investigated to model a whole serial link equalization including transmitter feed forward equalizer (FFE), receiver continuous time linear equalizer (CTLE) and decision feedback equalizer (DFE). By training, validating and testing a lot of samples that meet the COM specification of 400GAUI-8 C2C, an effective ML model is generated and the maximum relative error is only 0.1 compared with computation results. At last 3 link configurations are discussed from the view of tradeoff between the link performance and cost, illustrating that our COM based ML modeling method can be applied to advanced serial link design for NRZ, PAM4 or even other higher level pulse amplitude modulation signal.

Deep neural networks (DNNs) provide excellent services in machine learning tasks such as image recognition, speech recognition, pattern recognition, and intrusion detection. However, an adversarial example created by adding a little noise to the original data can result in misclassification by the DNN and the human eye cannot tell the difference from the original data. For example, if an attacker creates a modified right-turn traffic sign that is incorrectly categorized by a DNN, an autonomous vehicle with the DNN will incorrectly classify the modified right-turn traffic sign as a U-Turn sign, while a human will correctly classify that changed sign as right turn sign. Such an adversarial example is a serious threat to a DNN. Recently, an adversarial example with multiple targets was introduced that causes misclassification by multiple models within each target class using a single modified image. However, it has the weakness that as the number of target models increases, the overall attack success rate decreases. Therefore, if there are multiple models that the attacker wishes to attack, the attacker must control the attack success rate for each model by considering the attack priority for each model. In this paper, we propose a priority adversarial example that considers the attack priority for each model in cases targeting multiple models. The proposed method controls the attack success rate for each model by adjusting the weight of the attack function in the generation process while maintaining minimal distortion. We used MNIST and CIFAR10 as data sets and Tensorflow as machine learning library. Experimental results show that the proposed method can control the attack success rate for each model by considering each model's attack priority while maintaining minimal distortion (average 3.95 and 2.45 with MNIST for targeted and untargeted attacks, respectively, and average 51.95 and 44.45 with CIFAR10 for targeted and untargeted attacks, respectively).

Multiparty computation (MPC) is a cryptographic method that enables a set of parties to compute an arbitrary joint function of the private inputs of all parties and does not reveal any information other than the output. MPC based on a secret sharing scheme (SS-MPC) and garbled circuit (GC) is known as the most common MPC schemes. Another cryptographic method, homomorphic encryption (HE), computes an arbitrary function represented as a circuit by using ciphertexts without decrypting them. These technologies are in a trade-off relationship for the communication/round complexities, and the computation cost. The private decision tree evaluation (PDTE) is one of the key applications of these technologies. There exist several constant-round PDTE protocols based on GC, HE, or the hybrid schemes that are secure even if a malicious adversary who can deviate from protocol specifications corrupts some parties. There also exist other protocols based only on SS-MPC that are secure only if a semi-honest adversary who follows the protocol specification corrupts some parties. However, to the best of our knowledge, there are currently no constant-round PDTE protocols based only on SS-MPC that are secure against a malicious adversary. In this work, we propose a constant-round four-party PDTE protocol that achieves malicious security. Our protocol provides the PDTE securely and efficiently even when the communication environment has a large latency.

In recent years, there has been an increasing trend of applying artificial intelligence in many different fields, which has a profound and direct impact on human life. Consequently, this raises the need to understand the principles of model making predictions. Since most current high-precision models are black boxes, neither the AI scientist nor the end-user profoundly understands what is happening inside these models. Therefore, many algorithms are studied to explain AI models, especially those in the image classification problem in computer vision such as LIME, CAM, GradCAM. However, these algorithms still have limitations, such as LIME's long execution time and CAM's confusing interpretation of concreteness and clarity. Therefore, in this paper, we will propose a new method called Segmentation - Class Activation Mapping (SeCAM)/ This method combines the advantages of these algorithms above while at simultaneously overcoming their disadvantages. We tested this algorithm with various models, including ResNet50, InceptionV3, and VGG16 from ImageNet Large Scale Visual Recognition Challenge (ILSVRC) data set. Outstanding results were achieved when the algorithm has met all the requirements for a specific explanation in a remarkably short space of time.

Recently, with the spread of Internet of Things (IoT) devices, embedded hardware devices have been used in a variety of everyday electrical items. Due to the increased demand for embedded hardware devices, some of the IC design and manufacturing steps have been outsourced to third-party vendors. Since malicious third-party vendors may insert malicious circuits, called hardware Trojans, into their products, developing an effective hardware-Trojan detection method is strongly required. In this paper, we propose 25 hardware-Trojan features focusing on the structure of trigger circuits for machine-learning-based hardware-Trojan detection. Combining the proposed features into 11 existing hardware-Trojan features, we totally utilize 36 hardware-Trojan features for classification. Then we classify the nets in an unknown netlist into a set of normal nets and Trojan nets based on a random-forest classifier. The experimental results demonstrate that the average true positive rate (TPR) becomes 64.2% and the average true negative rate (TNR) becomes 100.0%. They improve the average TPR by 14.8 points while keeping the average TNR compared to existing state-of-the-art methods. In particular, the proposed method successfully finds out Trojan nets in several benchmark circuits, which are not found by the existing method.

Basic characteristics for relating design and base station layout design in land mobile communications are provided through a propagation model for path loss prediction. Owing to the rapid annual increase in traffic data, the number of base stations has increased accordingly. Therefore, propagation models for various scenarios and frequency bands are necessitated. To solve problems optimization and creation methods using the propagation model, a path loss prediction method that merges multiple models in machine learning is proposed herein. The method is discussed based on measurement values from Kitakyushu-shi. In machine learning, the selection of input parameters and suppression of overlearning are important for achieving highly accurate predictions. Therefore, the acquisition of conventional models based on the propagation environment and the use of input parameters of high importance are proposed. The prediction accuracy for Kitakyushu-shi using the proposed method indicates a root mean square error (RMSE) of 3.68dB. In addition, predictions are performed in Narashino-shi to confirm the effectiveness of the method in other urban scenarios. Results confirm the effectiveness of the proposed method for the urban scenario in Narashino-shi, and an RMSE of 4.39dB is obtained for the accuracy.

Magnetic fields are often utilized for position sensing of mobile devices. In typical sensing systems, multiple sensors are used to detect magnetic fields generated by target devices. To determine the positions of the devices, magnetic-field data detected by the sensors must be converted to device-position data. The data conversion is not trivial because it is a nonlinear inverse problem. In this study, we propose a machine-learning approach suitable for data conversion required in the magnetic-field-based position sensing of target devices. In our approach, two different sets of training data are used. One of the training datasets is composed of raw data of magnetic fields to be detected by sensors. The other set is composed of logarithmically represented data of the fields. We can obtain two different predictor functions by learning with these training datasets. Results show that the prediction accuracy of the target position improves when the two different predictor functions are used. Based on our simulation, the error of the target position estimated with the predictor functions is within 10cm in a 2m × 2m × 2m cubic space for 87% of all the cases of the target device states. The computational time required for predicting the positions of the target device is 4ms. As the prediction method is accurate and rapid, it can be utilized for the real-time tracking of moving objects and people.