The static deployment of Virtualized Network Functions (VNFs) introduces 1) significant degradation of Quality of Service (QoS), 2) inefficiency in the network and computing resource utilization, and 3) Network Function Virtualization (NFV)-based services with insufficient scalability, optimality, and flexibility. Caching VNFs is a promising solution to satisfy the dynamic demand to deploy a variety of VNFs and to maximize the performance as well as cost effectiveness. Although the concept of Content Delivery Network (CDN) is popular for efficiently caching and distributing contents, VNF deployment does not realize the benefit of CDN-based caching approaches. The challenges to caching VNFs are 1) to cover the large variety of VNFs and their properties, including the necessity of service chaining, and 2) to achieve high acceptance ratio given the limited availability of resources. This paper proposes Function Delivery Network (FDN), which is a cluster of distributed edge hypervisors for caching VNFs over a Software-Defined Network (SDN). The deployment and quality of the network function can be significantly improved by serving them closer to the end-users from the cached VNFs. FDN introduces a new strategy called Value-based caching that considers 1) the locality of reference and performance parameters of network and edge hypervisors together and 2) a partial deployment of service chains across multiple edge hypervisors for further efficient utilization of hypervisors resources. Evaluations on different patterns of input requests confirm that Value-based caching introduces significant improvement on both QoS and resource utilization in NFV.

This paper presents a real-time body motion classification system using the radio channel characteristics of a wearable body area network (BAN). We developed a custom wearable BAN radio channel measurement system by modifying an off-the-shelf ZigBee-based sensor network system, where the link quality indicator (LQI) values of the wireless links between the coordinator and four sensor nodes can be measured. After interpolating and standardizing the raw data samples in a pre-processing stage, the time-domain features are calculated, and the body motion is classified by a decision-tree based random forest machine learning algorithm which is most suitable for real-time processing. The features were carefully chosen to exclude those that exhibit the same tendency based on the mean and variance of the features to avoid overfitting. The measurements demonstrated successful real-time body motion classification and revealed the potential for practical use in various daily-life applications.

Homotopy algorithm provides a very powerful approach to select the best regularization term for the l1-norm minimization problem, but it is lack of provision for handling singularities. The singularity problem might be frequently encountered in practical implementations if the measurement matrix contains duplicate columns, approximate columns or columns with linear dependent in kernel space. The existing method for handling Homotopy singularities introduces a high-dimensional random ridge term into the measurement matrix, which has at least two shortcomings: 1) it is very difficult to choose a proper ridge term that applies to several different measurement matrices; and 2) the high-dimensional ridge term may accumulatively degrade the recovery performance for large-scale applications. To get around these shortcomings, a modified ridge-adding method is proposed to deal with the singularity problem, which introduces a low-dimensional random ridge vector into the l1-norm minimization problem directly. Our method provides a much simpler implementation, and it can alleviate the degradation caused by the ridge term because the dimension of ridge term in the proposed method is much smaller than the original one. Moreover, the proposed method can be further extended to handle the SVMpath initialization singularities. Theoretical analysis and experimental results validate the performance of the proposed method.

Mobile wireless sensor networks (WSNs) are facing threats from malicious nodes that disturb packet transmissions, leading to poor mobile WSN performance. Existing studies have proposed a number of methods, such as decision tree-based classification methods and reputation based methods, to detect these malicious nodes. These methods assume that the malicious nodes follow only pre-defined attack models and have no learning ability. However, this underestimation of the capability of malicious node is inappropriate due to recent rapid progresses in machine learning technologies. In this study, we design reinforcement learning-based malicious nodes, and define a novel observation space and sparse reward function for the reinforcement learning. We also design an adaptive learning method to detect these smart malicious nodes. We construct a robust classifier, which is frequently updated, to detect these smart malicious nodes. Extensive experiments show that, in contrast to existing attack models, the developed malicious nodes can degrade network performance without being detected. We also investigate the performance of our detection method, and confirm that the method significantly outperforms the state-of-the-art methods in terms of detection accuracy and false detection rate.

This paper analyzes the optimal SSD configuration including emerging non-volatile memories such as quadruple-level cell (QLC) NAND flash memory [1] and storage class memories (SCMs). First, SSD performance and SSD endurance lifetime of hybrid SSD are evaluated in four configurations: 1) single-level cell (SLC)/QLC NAND flash, 2) SCM/QLC NAND flash, 3) SCM/triple-level cell (TLC)/QLC NAND flash and 4) SCM/TLC NAND flash. Furthermore, these four configurations are compared in limited cost. In case of cold workloads or high total SSD cost assumption, SCM/TLC NAND flash hybrid configuration is recommended in both SSD performance and endurance lifetime. For hot workloads with low total SSD cost assumption, however, SLC/QLC NAND flash hybrid configuration is recommended with emphasis on SSD endurance lifetime. Under the same conditions as above, SCM/TLC/QLC NAND flash tri-hybrid is the best configuration in SSD performance considering cost. In particular, for prxy_0 (write-hot workload), SCM/TLC/QLC NAND flash tri-hybrid achieves 67% higher IOPS/cost than SCM/TLC NAND flash hybrid. Moreover, the configurations with the highest IOPS/cost in each workload and cost limit are picked up and analyzed with various types of SCMs. For all cases except for the case of prxy_1 with high total SSD cost assumption, middle-end SCM (write latency: 1us, read latency: 1us) is recommended in performance considering cost. However, for prxy_1 (read-hot workload) with high total SSD cost assumption, high-end SCM (write latency: 100ns, read latency: 100ns) achieves the best performance.

Malicious attackers on the Internet use automated attack programs to disrupt the use of services via mass spamming, unnecessary bulletin boarding, and account creation. Completely automated public turing test to tell computers and humans apart (CAPTCHA) is used as a security solution to prevent such automated attacks. CAPTCHA is a system that determines whether the user is a machine or a person by providing distorted letters, voices, and images that only humans can understand. However, new attack techniques such as optical character recognition (OCR) and deep neural networks (DNN) have been used to bypass CAPTCHA. In this paper, we propose a method to generate CAPTCHA images by using the fast-gradient sign method (FGSM), iterative FGSM (I-FGSM), and the DeepFool method. We used the CAPTCHA image provided by python as the dataset and Tensorflow as the machine learning library. The experimental results show that the CAPTCHA image generated via FGSM, I-FGSM, and DeepFool methods exhibits a 0% recognition rate with ε=0.15 for FGSM, a 0% recognition rate with α=0.1 with 50 iterations for I-FGSM, and a 45% recognition rate with 150 iterations for the DeepFool method.

Since deep learning was introduced, a series of achievements has been published in the field of automatic machine translation (MT). However, Korean-Vietnamese MT systems face many challenges because of a lack of data, multiple meanings of individual words, and grammatical diversity that depends on context. Therefore, the quality of Korean-Vietnamese MT systems is still sub-optimal. This paper discusses a method for applying Named Entity Recognition (NER) and Part-of-Speech (POS) tagging to Vietnamese sentences to improve the performance of Korean-Vietnamese MT systems. In terms of implementation, we used a tool to tag NER and POS in Vietnamese sentences. In addition, we had access to a Korean-Vietnamese parallel corpus with more than 450K paired sentences from our previous research paper. The experimental results indicate that tagging NER and POS in Vietnamese sentences can improve the quality of Korean-Vietnamese Neural MT (NMT) in terms of the Bi-Lingual Evaluation Understudy (BLEU) and Translation Error Rate (TER) score. On average, our MT system improved by 1.21 BLEU points or 2.33 TER scores after applying both NER and POS tagging to the Vietnamese corpus. Due to the structural features of language, the MT systems in the Korean to Vietnamese direction always give better BLEU and TER results than translation machines in the reverse direction.

We propose a multi-targeted backdoor that misleads different models to different classes. The method trains multiple models with data that include specific triggers that will be misclassified by different models into different classes. For example, an attacker can use a single multi-targeted backdoor sample to make model A recognize it as a stop sign, model B as a left-turn sign, model C as a right-turn sign, and model D as a U-turn sign. We used MNIST and Fashion-MNIST as experimental datasets and Tensorflow as a machine learning library. Experimental results show that the proposed method with a trigger can cause misclassification as different classes by different models with a 100% attack success rate on MNIST and Fashion-MNIST while maintaining the 97.18% and 91.1% accuracy, respectively, on data without a trigger.

The advancement of multicore technology has made hundreds or even thousands of cores processor on a single chip possible. However, on a larger scale multicore, a hardware-based cache coherency mechanism becomes overwhelmingly complicated, hot, and expensive. Therefore, we propose a software coherence scheme managed by a parallelizing compiler for shared-memory multicore systems without a hardware cache coherence mechanism. Our proposed method is simple and efficient. It is built into OSCAR automatic parallelizing compiler. The OSCAR compiler parallelizes the coarse grain task, analyzes stale data and line sharing in the program, then solves those problems by simple program restructuring and data synchronization. Using our proposed method, we compiled 10 benchmark programs from SPEC2000, SPEC2006, NAS Parallel Benchmark (NPB), and MediaBench II. The compiled binaries then are run on Renesas RP2, an 8 cores SH-4A processor, and a custom 8-core Altera Nios II system on Altera Arria 10 FPGA. The cache coherence hardware on the RP2 processor is only available for up to 4 cores. The RP2's cache coherence hardware can also be turned off for non-coherence cache mode. The Nios II multicore system does not have any hardware cache coherence mechanism; therefore, running a parallel program is difficult without any compiler support. The proposed method performed as good as or better than the hardware cache coherence scheme while still provided the correct result as the hardware coherence mechanism. This method allows a massive array of shared memory CPU cores in an HPC setting or a simple non-coherent multicore embedded CPU to be easily programmed. For example, on the RP2 processor, the proposed software-controlled non-coherent-cache (NCC) method gave us 2.6 times speedup for SPEC 2000 “equake” with 4 cores against sequential execution while got only 2.5 times speedup for 4 cores MESI hardware coherent control. Also, the software coherence control gave us 4.4 times speedup for 8 cores with no hardware coherence mechanism available.

Since a concept can be represented by different vocabularies, styles, and levels of detail, a translation task resembles a many-to-many mapping task from a distribution of sentences in the source language into a distribution of sentences in the target language. This viewpoint, however, is not fully implemented in current neural machine translation (NMT), which is one-to-one sentence mapping. In this study, we represent the distribution itself as multiple paraphrase sentences, which will enrich the model context understanding and trigger it to produce numerous hypotheses. We use a visually grounded paraphrase (VGP), which uses images as a constraint of the concept in paraphrasing, to guarantee that the created paraphrases are within the intended distribution. In this way, our method can also be considered as incorporating image information into NMT without using the image itself. We implement this idea by crowdsourcing a paraphrasing corpus that realizes VGP and construct neural paraphrasing that behaves as expert models in a NMT. Our experimental results reveal that our proposed VGP augmentation strategies showed improvement against a vanilla NMT baseline.

Attention mechanism, which selectively focuses on source-side information to learn a context vector for generating target words, has been shown to be an effective method for neural machine translation (NMT). In fact, generating target words depends on not only the source-side information but also the target-side information. Although the vanilla NMT can acquire target-side information implicitly by recurrent neural networks (RNN), RNN cannot adequately capture the global relationship between target-side words. To solve this problem, this paper proposes a novel target-attention approach to capture this information, thus enhancing target word predictions in NMT. Specifically, we propose three variants of target-attention model to directly obtain the global relationship among target words: 1) a forward target-attention model that uses a target attention mechanism to incorporate previous historical target words into the prediction of the current target word; 2) a reverse target-attention model that adopts a reverse RNN model to obtain the entire reverse target words information, and then to combine with source context information to generate target sequence; 3) a bidirectional target-attention model that combines the forward target-attention model and reverse target-attention model together, which can make full use of target words to further improve the performance of NMT. Our methods can be integrated into both RNN based NMT and self-attention based NMT, and help NMT get global target-side information to improve translation performance. Experiments on the NIST Chinese-to-English and the WMT English-to-German translation tasks show that the proposed models achieve significant improvements over state-of-the-art baselines.

Detecting Android malwares is imperative. As a promising Android malware detection scheme, we focus on the scheme leveraging the differences of traffic patterns between benign apps and malwares. Those differences can be captured even if the packet is encrypted. However, since such features are just statistic based ones, they cannot identify whether each traffic is malicious. Thus, it is necessary to design the scheme which is applicable to encrypted traffic data and supports identification of malicious traffic. In this paper, we propose an Android malware detection scheme based on level of SSL server certificate. Attackers tend to use an untrusted certificate to encrypt malicious payloads in many cases because passing rigorous examination is required to get a trusted certificate. Thus, we utilize SSL server certificate based features for detection since their certificates tend to be untrusted. Furthermore, in order to obtain the more exact features, we introduce required permission based weight values because malwares inevitably require permissions regarding malicious actions. By computer simulation with real dataset, we show our scheme achieves an accuracy of 92.7%. True positive rate and false positive rate are 5.6% higher and 3.2% lower than the previous scheme, respectively. Our scheme can cope with encrypted malicious payloads and 89 malwares which are not detected by the previous scheme.

A key driver of software business growth in developing countries is the survival of software small and medium-sized enterprises (SMEs). Quality of products is a critical factor that can indicate the future of the business by building customer confidence. Software development agencies need to be aware of meeting international standards in software development process. In practice, consultants and assessors are usually employed as the primary solution, which can impact the budget in case of small businesses. Self-assessment tools for software development process can potentially reduce time and cost of formal assessment for software SMEs. However, the existing support methods and tools are largely insufficient in terms of process coverage and semi-automated evaluation. This paper proposes to apply a knowledge-based approach in development of a self-assessment and gap analysis support system for the ISO/IEC 29110 standard. The approach has an advantage that insights from domain experts and the standard are captured in the knowledge base in form of decision tables that can be flexibly managed. Our knowledge base is unique in that task lists and work products defined in the standard are broken down into task and work product characteristics, respectively. Their relation provides the links between Task List and Work Product which make users more understand and influence self-assessment. A prototype support system was developed to assess the level of software development capability of the agencies based on the ISO/IEC 29110 standard. A preliminary evaluation study showed that the system can improve performance of users who are inexperienced in applying ISO/IEC 29110 standard in terms of task coverage and user's time and effort compared to the traditional self-assessment method.

Register-transfer-level (RTL) information is hardly available for hardware Trojan detection. In this paper, four RTL Trojan features related to branching statement are proposed. The Minimum Redundancy Maximum Relevance (mRMR) feature selection is applied to the proposed Trojan features to determine the recommended feature combinations. The feature combinations are then tested using different machine learning concepts in order to determine the best approach for classifying Trojan and normal branches. The result shows that a Decision Tree classification algorithm with all the four proposed Trojan features can achieve an average true positive detection rate of 93.72% on unseen test data.

This paper proposes a release-aware bug triaging method that aims to increase the number of bugs that developers can fix by the next release date during open-source software development. A variety of methods have been proposed for recommending appropriate developers for particular bug-fixing tasks, but since these approaches only consider the developers' ability to fix the bug, they tend to assign many of the bugs to a small number of the project's developers. Since projects generally have a release schedule, even excellent developers cannot fix all the bugs that are assigned to them by the existing methods. The proposed method places an upper limit on the number of tasks which are assigned to each developer during a given period, in addition to considering the ability of developers. Our method regards the bug assignment problem as a multiple knapsack problem, finding the best combination of bugs and developers. The best combination is one that maximizes the efficiency of the project, while meeting the constraint where it can only assign as many bugs as the developers can fix during a given period. We conduct the case study, applying our method to bug reports from Mozilla Firefox, Eclipse Platform and GNU compiler collection (GCC). We find that our method has the following properties: (1) it can prevent the bug-fixing load from being concentrated on a small number of developers; (2) compared with the existing methods, the proposed method can assign a more appropriate amount of bugs that each developer can fix by the next release date; (3) it can reduce the time taken to fix bugs by 35%-41%, compared with manual bug triaging;

As one type of machine-learning model, a “decision-tree ensemble model” (DTEM) is represented by a set of decision trees. A DTEM is mainly known to be valid for structured data; however, like other machine-learning models, it is difficult to train so that it returns the correct output value (called “prediction value”) for any input value (called “attribute value”). Accordingly, when a DTEM is used in regard to a system that requires reliability, it is important to comprehensively detect attribute values that lead to malfunctions of a system (failures) during development and take appropriate countermeasures. One conceivable solution is to install an input filter that controls the input to the DTEM and to use separate software to process attribute values that may lead to failures. To develop the input filter, it is necessary to specify the filtering condition for the attribute value that leads to the malfunction of the system. In consideration of that necessity, we propose a method for formally verifying a DTEM and, according to the result of the verification, if an attribute value leading to a failure is found, extracting the range in which such an attribute value exists. The proposed method can comprehensively extract the range in which the attribute value leading to the failure exists; therefore, by creating an input filter based on that range, it is possible to prevent the failure. To demonstrate the feasibility of the proposed method, we performed a case study using a dataset of house prices. Through the case study, we also evaluated its scalability and it is shown that the number and depth of decision trees are important factors that determines the applicability of the proposed method.

Interpretability has become an important issue in the machine learning field, along with the success of layered neural networks in various practical tasks. Since a trained layered neural network consists of a complex nonlinear relationship between large number of parameters, we failed to understand how they could achieve input-output mappings with a given data set. In this paper, we propose the non-negative task matrix decomposition method, which applies non-negative matrix factorization to a trained layered neural network. This enables us to decompose the inference mechanism of a trained layered neural network into multiple principal tasks of input-output mapping, and reveal the roles of hidden units in terms of their contribution to each principal task.

With the recent advances in e-commerce, it has become important to recommend not only mass-produced daily items, such as books, but also items that are not mass-produced. In this study, we present an algorithm for real estate recommendations. Automatic property recommendations are a highly difficult task because no identical properties exist in the world, occupied properties cannot be recommended, and users rent or buy properties only a few times in their lives. For the first step of property recommendation, we predict users' preferences for properties by combining content-based filtering and Multi-Layer Perceptron (MLP). In the MLP, we use not only attribute data of users and properties, but also deep features extracted from property floor plan images. As a result, we successfully predict users' preference with a Matthews Correlation Coefficient (MCC) of 0.166.

In this article, we propose a data framework for edge computing that allows developers to easily attain efficient data transfer between mobile devices or users. We propose a distributed key-value storage platform for edge computing and its explicit data distribution management method that follows the publish/subscribe relationships specific to applications. In this platform, edge servers organize the distributed key-value storage in a uniform namespace. To enable fast data access to a record in edge computing, the allocation strategy of the record and its cache on the edge servers is important. Our platform offers distributed objects that can dynamically change their home server and allocate cache objects proactively following user-defined rules. A rule is defined in a declarative manner and specifies where to place cache objects depending on the status of the target record and its associated records. The system can reflect record modification to the cached records immediately. We also integrate a push notification system using WebSocket to notify events on a specified table. We introduce a messaging service application between mobile appliances and several other applications to show how cache rules apply to them. We evaluate the performance of our system using some sample applications.

The arms race between offense and defense in the cloud impels the innovation of techniques for monitoring attacks and unauthorized activities. The promising technique of virtual machine introspection (VMI) becomes prevalent for its tamper-resistant capability. However, some elaborate exploitations are capable of invalidating VMI-based tools by breaking the assumption of a trusted guest kernel. To achieve a more reliable and robust introspection, we introduce a practical approach to monitor and detect attacks that attempt to subvert VMI in this paper. Our approach combines supervised machine learning and hardware architectural events to identify those malicious behaviors which are targeted at VMI techniques. To demonstrate the feasibility, we implement a prototype named HyperMon on the Xen hypervisor. The results of our evaluation show the effectiveness of HyperMon in detecting malicious behaviors with an average accuracy of 90.51% (AUC).