LINE is currently the most popular messaging service in Japan. Communications using LINE are protected by the original encryption scheme, called LINE Encryption, and specifications of the client-to-server transport encryption protocol and the client-to-client message end-to-end encryption protocol are published by the Technical Whitepaper. Though a spoofing attack (i.e., a malicious client makes another client misunderstand the identity of the peer) and a reply attack (i.e., a message in a session is sent again in another session by a man-in-the-middle adversary, and the receiver accepts these messages) to the end-to-end protocol have been shown, no formal security analysis of these protocols is known. In this paper, we show a formal verification result of secrecy of application data and authenticity for protocols of LINE Encryption (Version 1.0) by using the automated security verification tool ProVerif. Especially, since it is claimed that the transport protocol satisfies forward secrecy (i.e., even if the static private key is leaked, security of application data is guaranteed), we verify forward secrecy for client's data and for server's data of the transport protocol, and we find an attack to break secrecy of client's application data. Moreover, we find the spoofing attack and the reply attack, which are reported in previous papers.
Since software becomes more complex during its life cycle, the verification cost becomes higher, especially for such methods which are using model checking in general and assume-guarantee reasoning in specific. To address the problem of reducing the assume-guarantee verification cost, this paper presents a method to generate locally minimum and strongest assumptions for verification of component-based software. For this purpose, we integrate a variant of membership queries answering technique to an algorithm which considers candidate assumptions that are smaller and stronger first, larger and weaker later. Because the algorithm stops as soon as it reaches a conclusive result, the generated assumptions are the locally minimum and strongest ones. The correctness proof of the proposed algorithm is also included in the paper. An implemented tool, test data, and experimental results are presented and discussed.
Refinement-based formal specification is a promising approach to the increasing complexity of software systems, as demonstrated in the formal method Event-B. It allows stepwise modeling and verifying of complex systems with multiple steps at different abstraction levels. However, making changes is more difficult, as caution is necessary to avoid breaking the consistency between the steps. Judging whether a change is valid or not is a non-trivial task, as the logical dependency relationships between the modeling elements (predicates) are implicit and complex. In this paper, we propose a method for analyzing the impact of the changes of Event-B. By attaching labels to modeling elements (predicates), the method helps engineers understand how a model is structured and what needs to be modified to accomplish a change.
The scale of scientific data generated by experimental facilities and simulations in high-performance computing facilities has been proliferating with the emergence of IoT-based big data. In many cases, this data must be transmitted rapidly and reliably to remote facilities for storage, analysis, or sharing, for the Internet of Things (IoT) applications. Simultaneously, IoT data can be verified using a checksum after the data has been written to the disk at the destination to ensure its integrity. However, this end-to-end integrity verification inevitably creates overheads (extra disk I/O and more computation). Thus, the overall data transfer time increases. In this article, we evaluate strategies to maximize the overlap between data transfer and checksum computation for astronomical observation data. Specifically, we examine file-level and block-level (with various block sizes) pipelining to overlap data transfer and checksum computation. We analyze these pipelining approaches in the context of GridFTP, a widely used protocol for scientific data transfers. Theoretical analysis and experiments are conducted to evaluate our methods. The results show that block-level pipelining is effective in maximizing the overlap mentioned above, and can improve the overall data transfer time with end-to-end integrity verification by up to 70% compared to the sequential execution of transfer and checksum, and by up to 60% compared to file-level pipelining.
Accurate estimation of the state-of-charge is a crucial need for the battery, which is the most important power source in electric vehicles. To achieve better estimation result, an accurate battery model with optimum parameters is required. In this paper, a gradient-free optimization technique, namely tree seed algorithm (TSA), is utilized to identify specific parameters of the battery model. In order to strengthen the search ability of TSA and obtain more quality results, the original algorithm is improved. On one hand, the DE/rand/2/bin mechanism is employed to maintain the colony diversity, by generating mutant individuals in each time step. On the other hand, the control parameter in the algorithm is adaptively updated during the searching process, to achieve a better balance between the exploitation and exploration capabilities. The battery state-of-charge can be estimated simultaneously by regarding it as one of the parameters. Experiments under different dynamic profiles show that the proposed method can provide reliable and accurate estimation results. The performance of conventional algorithms, such as genetic algorithm and extended Kalman filter, are also compared to demonstrate the superiority of the proposed method in terms of accuracy and robustness.
Java is one of important program language today. In Java, in order to build sound software, we have to carefully implement two fundamental methods hashCode and equals. This requirement, however, is not easy to follow in real software development. Some existing studies for ensuring the correctness of these two methods rely on static analysis, which are limited to loop-free programs. This paper proposes a new solution to this important problem, using software analysis workbench (SAW), an open source tool. The efficiency is evaluated through experiments. We also provide a useful situation where cost of regression testing is reduced when program refactoring is conducted.
Symbolic execution is capable of automatically generating tests that achieve high coverage. However, its practical use is limited by the scalability problem. To mitigate it, this paper proposes State Concretization based Symbolic Execution (SCSE). SCSE speeds up symbolic execution via state concretization. Specifically, by introducing a concrete store, our approach avoids invoking the constraint solver to check path feasibility at conditional instructions. Intuitively, there is no need to check the feasibility of a path along a concrete execution since it is always feasible. With state concretization, the number of solver queries greatly decreases, thus improving the efficiency of symbolic execution. Through experimental evaluation on real programs, we show that state concretization helps to speed up symbolic execution significantly.
The traditional recommendation system (RS) can learn the potential personal preferences of users and potential attribute characteristics of items through the rating records between users and items to make recommendations.However, for the new items with no historical rating records,the traditional RS usually suffers from the typical cold start problem. Additional auxiliary information has usually been used in the item cold start recommendation,we further bring temporal dynamics,text and relevance in our models to release item cold start.Two new cold start recommendation models TmTx(Time,Text) and TmTI(Time,Text,Item correlation) proposed to solve the item cold start problem for different cold start scenarios.While well-known methods like TimeSVD++ and CoFactor partially take temporal dynamics,comments,and item correlations into consideration to solve the cold start problem but none of them combines these information together.Two models proposed in this paper fused features such as time,text,and relevance can effectively improve the performance under item cold start.We select the convolutional neural network (CNN) to extract features from item description text which provides the model the ability to deal with cold start items.Both proposed models can effectively improve the performance with item cold start.Experimental results on three real-world data set show that our proposed models lead to significant improvement compared with the baseline methods.
Accurate traffic flow prediction is the precondition for many applications in Intelligent Transportation Systems, such as traffic control and route guidance. Traditional data driven traffic flow prediction models tend to ignore traffic self-features (e.g., periodicities), and commonly suffer from the shifts brought by various complex factors (e.g., weather and holidays). These would reduce the precision and robustness of the prediction models. To tackle this problem, in this paper, we propose a CNN-based multi-feature predictive model (MF-CNN) that collectively predicts network-scale traffic flow with multiple spatiotemporal features and external factors (weather and holidays). Specifically, we classify traffic self-features into temporal continuity as short-term feature, daily periodicity and weekly periodicity as long-term features, then map them to three two-dimensional spaces, which each one is composed of time and space, represented by two-dimensional matrices. The high-level spatiotemporal features learned by CNNs from the matrices with different time lags are further fused with external factors by a logistic regression layer to derive the final prediction. Experimental results indicate that the MF-CNN model considering multi-features improves the predictive performance compared to five baseline models, and achieves the trade-off between accuracy and efficiency.
This paper proposes a computationally efficient offline semi-supervised algorithm that yields a more accurate prediction than the label propagation algorithm, which is commonly used in online graph-based semi-supervised learning (SSL). Our proposed method is an offline method that is intended to assist online graph-based SSL algorithms. The efficacy of the tool in creating new learning algorithms of this type is demonstrated in numerical experiments.
Conventional approaches to statistical parametric speech synthesis use context-dependent hidden Markov models (HMMs) clustered using decision trees to generate speech parameters from linguistic features. However, decision trees are not always appropriate to model complex context dependencies of linguistic features efficiently. An alternative scheme that replaces decision trees with deep neural networks (DNNs) was presented as a possible way to overcome the difficulty. By training the network to represent high-dimensional feedforward dependencies from linguistic features to acoustic features, DNN-based speech synthesis systems convert a text into a speech. To improved the naturalness of the synthesized speech, this paper presents a novel pre-training method for DNN-based statistical parametric speech synthesis systems. In our method, a deep relational model (DRM), which represents a joint probability of two visible variables, is applied to describe the joint distribution of acoustic and linguistic features. As with DNNs, a DRM consists several hidden layers and two visible layers. Although DNNs represent feedforward dependencies from one visible variables (inputs) to other visible variables (outputs), a DRM has an ability to represent the bidirectional dependencies between two visible variables. During the maximum-likelihood (ML) -based training, the model optimizes its parameters (connection weights between two adjacent layers, and biases) of a deep architecture considering the bidirectional conversion between 1) acoustic features given linguistic features, and 2) linguistic features given acoustic features generated from itself. Owing to considering whether the generated acoustic features are recognizable, our method can obtain reasonable parameters for speech synthesis. Experimental results in a speech synthesis task show that pre-trained DNN-based systems using our proposed method outperformed randomly-initialized DNN-based systems, especially when the amount of training data is limited. Additionally, speaker-dependent speech recognition experimental results also show that our method outperformed DNN-based systems, by setting the initial parameters of our method are the same as that in the synthesis experiments.
This paper presents recognition of anomalously deformed Kana sequences in Japanese historical documents, for which a contest was held by IEICE PRMU 2017. The contest was divided into three levels in accordance with the number of characters to be recognized: level 1: single characters, level 2: sequences of three vertically written Kana characters, and level 3: unrestricted sets of characters composed of three or more characters possibly in multiple lines. This paper focuses on the methods for levels 2 and 3 that won the contest. We basically follow the segmentation-free approach and employ the hierarchy of a Convolutional Neural Network (CNN) for feature extraction, Bidirectional Long Short-Term Memory (BLSTM) for frame prediction, and Connectionist Temporal Classification (CTC) for text recognition, which is named a Deep Convolutional Recurrent Network (DCRN). We compare the pretrained CNN approach and the end-to-end approach with more detailed variations for level 2. Then, we propose a method of vertical text line segmentation and multiple line concatenation before applying DCRN for level 3. We also examine a two-dimensional BLSTM (2DBLSTM) based method for level 3. We present the evaluation of the best methods by cross validation. We achieved an accuracy of 89.10% for the three-Kana-character sequence recognition and an accuracy of 87.70% for the unrestricted Kana recognition without employing linguistic context. These results prove the performances of the proposed models on the level 2 and 3 tasks.
We present an OpenACC-based parallelization implementation of stochastic algorithms for simulating biochemical reaction networks on modern GPUs (graphics processing units). To investigate the effectiveness of using OpenACC for leveraging the massive hardware parallelism of the GPU architecture, we carefully apply OpenACC's language constructs and mechanisms to implementing a parallel version of stochastic simulation algorithms on the GPU. Using our OpenACC implementation in comparison to both the NVidia CUDA and the CPU-based implementations, we report our initial experiences on OpenACC's performance and programming productivity in the context of GPU-accelerated scientific computing.
Hadoop, a distributed processing framework for big-data, is now widely used for multimedia processing. However, when processing video data from a Hadoop distributed file system (HDFS), unnecessary network traffic is generated due to an inefficient HDFS block slice policy for picture frames in video files. We propose a new block replication policy to solve this problem and compare the newly proposed HDFS with the original HDFS via extensive experiments. The proposed HDFS reduces network traffic, and increases locality between processing cores and file locations.
In this paper, a smart dressing system was implemented based on flexible pH sensors that can monitor the infection of a wounded area by tracking the pH value of the area. Motivated by the fabrication process widely used for semiconductors, the flexible pH sensor fabrication process was devised with a polyester (PET) film and a Si wafer, which deposits Au and Ag on a PET film. Because the electrodes are comprised of a working electrode and a reference electrode, the reference electrode was fabricated by synthesizing the Polyaniline (PANI) on Ag/AgCl, while the pH sensor has four channels to evenly measure the pH value in a wide area. The smart dressing system was constructed with four pH sensors, a single temperature sensor, a level shifter, a regulator, an analog-to-digital converter (ADC), and a monitoring PC. The measurement results show that our smart dressing system has a size of 5×5cm2 and can monitor the pH value range found in [3,9] with a sensitivity slope of 50mV/pH.
Flash storage suffers from severe performance degradation due to its inherent internal synchronization overhead. Especially, flushing an L2P (logical address to physical address) mapping table significantly contributes to the performance degradation. To relieve the problem, we propose an efficient L2P mapping table management scheme on the flash storage, which works along with a small-sized NVRAM. It flushes L2P mapping table from DRAM to NVRAM or flash memory selectively. In our experiments, the proposed scheme shows up to 9.37× better performance than conventional schemes.
Nowadays, malware is a serious threat to the Internet. Traditional signature-based malware detection method can be easily evaded by code obfuscation. Therefore, many researchers use the high-level structure of malware like function call graph, which is impacted less from the obfuscation, to find the malware variants. However, existing graph match methods rely on approximate calculation, which are inefficient and the accuracy cannot be effectively guaranteed. Inspired by the successful application of graph convolutional network in node classification and graph classification, we propose a novel malware similarity metric method based on graph convolutional network. We use graph convolutional network to compute the graph embedding vectors, and then we calculate the similarity metric of two graph based on the distance between two graph embedding vectors. Experimental results on the Kaggle dataset show that our method can applied to the graph based malware similarity metric method, and the accuracy of clustering application with our method reaches to 97% with high time efficiency.
Deep Graphical Model (DGM) based on Generative Adversarial Nets (GANs) has shown promise in image generation and latent variable inference. One of the typical models is the Iterative Adversarial Inference model (GibbsNet), which learns the joint distribution between the data and its latent variable. We present RGNet (Re-inference GibbsNet) which introduces a re-inference chain in GibbsNet to improve the quality of generated samples and inferred latent variables. RGNet consists of the generative, inference, and discriminative networks. An adversarial game is cast between the generative and inference networks and the discriminative network. The discriminative network is trained to distinguish between (i) the joint inference-latent/data-space pairs and re-inference-latent/data-space pairs and (ii) the joint sampled-latent/generated-data-space pairs. We show empirically that RGNet surpasses GibbsNet in the quality of inferred latent variables and achieves comparable performance on image generation and inpainting tasks.
We introduce a method to estimate the attractiveness of a food photo. It extracts image features focusing on the appearances of 1) the entire food, and 2) the main ingredients. To estimate the attractiveness of an arbitrary food photo, these features are integrated in a regression scheme. We also constructed and released a food image dataset composed of images of ten food categories taken from 36 angles and accompanied with attractiveness values. Evaluation results showed the effectiveness of integrating the two kinds of image features.
Speech captured by an in-ear microphone placed inside an occluded ear has a high signal-to-noise ratio; however, it has different sound characteristics compared to normal speech captured through air conduction. In this study, a method for blind speech quality enhancement is proposed that can convert speech captured by an in-ear microphone to one that resembles normal speech. The proposed method estimates an input-dependent enhancement function by using a neural network in the feature domain and enhances the captured speech via time-domain filtering. Subjective and objective evaluations confirm that the speech enhanced using our proposed method sounds more similar to normal speech than that enhanced using conventional equalizer-based methods.
Due to improvements in hardware and software performance, deep learning algorithms have been used in many areas and have shown good results. In this paper, we propose a noise reduction framework based on a convolutional neural network (CNN) with deconvolution and a modified residual network (ResNet) to remove image noise. Simulation results show that the proposed algorithm is superior to the conventional noise eliminator in subjective and objective performance analyses.
Heat map is an important tool for eye tracking data analysis and visualization. It is very intuitive to express the area watched by observer, but ignores saccade information that expresses gaze shift. Based on conventional heat map generation method, this paper presents a novel heat map generation method for eye tracking data. The proposed method introduces a mixed data structure of fixation points and saccades, and considers heat map deformation for saccade type data. The proposed method has advantages on indicating gaze transition direction while visualizing gaze region.