Vol. 45, No. 8, Aug. 2018
Digital Library


A Defense Technique against ARP Spoofing Attacks using a Keystone Authentication Table in the OpenStack Cloud Environment

Hyo Sung Kang, Choong Seon Hong

http://doi.org/10.5626/JOK.2018.45.8.755

Recently cloud service has been introduced to enable many enterprises to achieve their purposes such as improving efficiency, reducing costs, and revolutionizing business processes. However spoofing or poison attacks on VM inside the cloud deteriorate the cloud system and those attacks can be a stumbling block for spreading cloud services. To solve such problems, much research has been done, but it all seems to be impractical and limited in terms of finding techniques for detecting attacks and applying to large scale of networks. In this paper, we propose a way to prevent loss of VM resources because of such attacks on the OpenStack environment by using a reliable ARP table in a cloud computing environment and showing that the proposed mechanism is an effective way to defend against the ARP spoofing attacks.

Effective Parallel LiDAR Triangulated Irregular Network Construction Method Using Convex Boundary Triangle

Permata Nur Rizki, Sangyoon Oh

http://doi.org/10.5626/JOK.2018.45.8.761

A triangulated irregular network (TIN) model has been adopted in numerous digital mapping schemes to represent the terrain surfaces. With the TIN model, we can produce a more flexible resolution and a detailed surface compared to a grid-based model. However, TIN processing is computationally intensive and it requires an efficient approach in order to process massive Light Detection and Ranging (LiDAR) dataset. In this article, we present our parallelization method for LiDAR TIN construction using the MapReduce paradigm. We introduce a triangulation approach with a convex boundary triangle to reduce the number of vertices to visit - thereby reducing overhead from the data dependencies - in the parallel execution of the TIN construction. First, we divide a planar area vertically based on the information from the convex boundary region and allocate the initial LiDAR point cloud to parallel workers. Then, we apply our justification rules in each parallel process to prevent the Delaunay property violation in the boundary triangles. Lastly, the constructed triangles from each of the workers are merged based on 〈key,value〉 intermediate metadata properties. To evaluate the effectiveness of our proposed method, we used Apache Spark. The empirical results of the experiment show that our method outperforms the conventional method by having 16.2% less processed vertices.

A Study on Two-dimensional Array-based Technology to Identify Obfuscatied Malware

Seonbin Hwang, Hogyeong Kim, Junho Hwang, Taejin Lee

http://doi.org/10.5626/JOK.2018.45.8.769

More than 1.6 milion types of malware are emerging on average per day, and most cyber attackes are generated by malware. Moreover, malware obfuscation techniques are becoming more intelligent through packing or encryption to prevent reverse engineering analysis. In the case of static analysis, there is a limit to the analysis when the analytical file becomes obfuscated, and a countermeasure is needed. In this paper, we propose an approach based on String, Symbol, and Entropy as a way to identify malware even during obfuscation. Two-dimensional arrays were applied for fixed feature-set processing as well as non-fixed feature-set processing, and 15,000 malware/benign samples were tested using the Deep Neural Network. This study is expected to operate in a complementary manner in conjunction with various malicious code detection methods in the future, and it is expected that it can be utilized in the analysis of obfuscated malware variants.

Parallel Computation of Z-Function for Order-Preserving Pattern Matching and Order-Preserving Multiple Pattern Matching

Youkun Shin, Youngho Kim, Jeong Seop Sim

http://doi.org/10.5626/JOK.2018.45.8.778

Given a text T of length n and a pattern P of length m, the order-preserving pattern matching problem is to find all substrings in T which are order-isomorphic to P. Given a text T of length n and a set of patterns W={P₁, P₂,…, Pb}, the order-preserving multiple pattern matching problem is to find all substrings in T which are order-isomorphic to patterns of W. In this paper, we present two parallel algorithms based on the Z-function. The first algorithm for the order-preserving pattern matching problem runs in O(m) time using O(n+hm) threads and the second algorithm for the order-preserving multiple pattern matching problem runs in O(n+M) time using O(b(n+M)) threads, where h is the number of blocks and M is the length of the longest pattern in W. Experimental results show that our parallel algorithm for the order-preserving pattern matching problem is approximately 71.2 times faster than the sequential algorithm when m=10 and n=1,000,000, and that our parallel algorithm for the order-preserving multiple pattern matching problem is approximately 12.2 times faster than the sequential algorithm when b=1,000, m=10, and n=1,000.

Backbone Network for Object Detection with Multiple Dilated Convolutions and Feature Summation

Vani Natalia Kuntjono, Seunghyun Ko, Yang Fang, Geunsik Jo

http://doi.org/10.5626/JOK.2018.45.8.786

The advancement of CNN leads to the trend of using very deep convolutional neural network which contains more than 100 layers not only for object detection, but also for image segmentation and object classification. However, deep CNN requires lots of resources, and so is not suitable for people who have limited resources or real time requirements. In this paper, we propose a new backbone network for object detection with multiple dilated convolutions and feature summation. Feature summation enables easier flow of gradients and minimizes loss of spatial information that is caused by convolving. By using multiple dilated convolution, we can widen the receptive field of individual neurons without adding more parameters. Furthermore, by using a shallow neural network as a backbone network, our network can be trained and used in an environment with limited resources and without pre-training it in ImageNet dataset. Experiments demonstrate we achieved 71% and 38.2% of accuracy on Pascal VOC and MS COCO dataset, respectively.

Research on Joint Models for Korean Word Spacing and POS (Part-Of-Speech) Tagging based on Bidirectional LSTM-CRF

Seon-Wu Kim, Sung-Pil Choi

http://doi.org/10.5626/JOK.2018.45.8.792

In general, Korean part-of-speech tagging is done on a sentence in which the spacing is completed by a word as an input. In order to process a sentence that is not properly spaced, automatic spacing is needed to correct the error. However, if the automatic spacing and the parts tagging are sequentially performed, a serious performance degradation may result from an error occurring at each step. In this study, we try to solve this problem by constructing an integrated model that can perform automatic spacing and POS(Part-Of-Speech) tagging simultaneously. Based on the Bidirectional LSTM-CRF model, we propose an integrated model that can simultaneously perform syllable-based word spacing and POS tagging complementarily. In the experiments using a Sejong tagged text, we obtained 98.77% POS tagging accuracy for the completely spaced sentences, and 97.92% morpheme accuracy for the sentences without any word spacing.

Progressive Visual Analytics Using Scagnostics and an Automatic Partitioning Variables Selection Method

DongHwa Shin, Sehi L’Yi, Hyunjoo Song, Jinwook Seo

http://doi.org/10.5626/JOK.2018.45.8.801

In this paper, we propose a visual analytics system that combines progressive visualization with a partitioning variables selection method, one of the analytic techniques based on a scagnostics concept. In order to overcome the problems of scalability and performance associated with the existing method, all of the interface elements are designed so as to update the analysis progress in real time. The interface consists of two parts: an overview of the scatterplots to be analyzed and a detailed view for exploring interesting scatterplots in detail. We introduce the design rationale of our system and present a data analysis scenario to show how users can effectively use the system.

A Linguistic Study of Speech Act and Automatic Speech Act Classification for Korean Tutorial Dialog

Youngeun Koo, Jiyoun Kim, Munpyo Hong, Youngkil Kim

http://doi.org/10.5626/JOK.2018.45.8.807

Speech act is a speaker’s intention of utterance in communication. To communicate successfully, we need to figure out speech act of a speaker’s utterance correctly. This paper proposed linguistic features of an utterance that affect speech act classification by analyzing Korean tutorial dialogue. Ultimately we hope this enables automatic speech act classification. Thirteen linguistically motivated features are suggested in this paper and verified with WEKA 3.8.1. The accuracy of the proposed linguistically motivated features of speech act classification reached 70.03%. Approximately 30%p of accuracy has improved compared to a baseline, using unigram and bigram as the only features of speech act classification.

Multi-sense Word Embedding to Improve Performance of a CNN-based Relation Extraction Model

Sangha Nam, Kijong Han, Eun-kyung Kim, Sunggoo Kwon, Yoosung Jung, Key-Sun Choi

http://doi.org/10.5626/JOK.2018.45.8.816

The relation extraction task is to classify a relation between two entities in an input sentence and is important in natural language processing and knowledge extraction. Many studies have designed a relation extraction model using a distant supervision method. Recently the deep-learning based relation extraction model became mainstream such as CNN or RNN. However, the existing studies do not solve the homograph problem of word embedding used as an input of the model. Therefore, model learning proceeds with a single embedding value of homogeneous terms having different meanings; that is, the relation extraction model is learned without grasping the meaning of a word accurately. In this paper, we propose a relation extraction model using multi-sense word embedding. In order to learn multi-sense word embedding, we used a word sense disambiguation module based on the CoreNet concept, and the relation extraction model used CNN and PCNN models to learn key words in sentences.

A Named-Entity Recognition Training Method Using Bagging-Based Bootstrapping

Yujin Jeong, Juae Kim, Youngjoong Ko, Jungyun Seo

http://doi.org/10.5626/JOK.2018.45.8.825

Most previous named-entity(NE) recognition studies have been based on supervised learning methods. Although supervised learning-based NE recognition has performed well, it requires a lot of time and cost to construct a large labeled corpus. In this paper, we propose an NE recognition training method that uses an automatically generated labeled corpus to solve this problem. Since the proposed method uses a large machine-labeled corpus, it can greatly reduce the time and cost needed to generate a labeled corpus manually. In addition, a bagging-based bootstrapping technique is applied to our method in order to correct errors from the machine-labeled data. As a result, experimental results show that the proposed method achieves the highest F1 score of 70.76% by adding the bagging-based bootstrapping technique, which is 5.17%p higher than that of the baseline system.

Object Recognition in Low Resolution Images using a Convolutional Neural Network and an Image Enhancement Network

Injae Choi, Jeongin Seo, Hyeyoung Park

http://doi.org/10.5626/JOK.2018.45.8.831

Recently, the development of deep learning technologies such as convolutional neural networks have greatly improved the performance of object recognition in images. However, object recognition still has many challenges due to large variations in images and the diversity of object categories to be recognized. In particular, studies on object recognition in low-resolution images are still in the primary stage and have not shown satisfactory performance. In this paper, we propose an image enhancement neural network to improve object recognition performance of low resolution images. We also use the enhanced images for training an object recognition model based on convolutional neural networks to obtain robust recognition performance with resolution changes. To verify the efficiency of the proposed method, we conducted computational experiments on object recognition in a low-resolution environment using the CIFAR-10 and CIFAR-100 databases. We confirmed that the proposed method can greatly improve the recognition performance in low-resolution images while keeping stable performance in the original resolution images.

An Approximate k-Nearest Neighbor Query Processing Method Based on a Dynamic Partitioning Grid Index in Distributed Processing Environments

Dojin Choi, Jongtae Lim, Kyoungsoo Bok, Jaesoo Yoo

http://doi.org/10.5626/JOK.2018.45.8.838

As smart devices continue to grow in popularity, various location-based services are increasingly provided to users. Some location-based social applications that combine social services and location-based services have a large number of users. The demands of a k-nearest neighbors (k-NN) query, which finds the k closest locations from a user location, are increased in services such as these. In this paper, we propose an approximate k-NN query processing method for real time response requirements for a dynamic partition based grid index. The proposed approximate k-NN query processing method first retrieves the related cells by considering a user movement. Then, we optimize cell searches in the dynamic partitioning method and grid index for the improvement of the accuracy of the proposed approximate k-NN query. The proposed method is implemented in Storm to perform efficient distributed processing in stream environments. In order to show the superiority of this method, we conduct various performance evaluations.

Algorithm for Detecting Double-Spending in Blockchain

Minho Kim, Sujin Kim, Hoon Choi

http://doi.org/10.5626/JOK.2018.45.8.848

The blockchain is a key technology of the Bitcoin, which is widely used as an electronic cash system. In the Bitcoin, one digital currency is valid for only one transaction. It is called double-spending, a type of illegal transaction, if two or more transactions are made by using the same digital currency. When the blockchain is forked, the blockchain specification assumes that the longer blockchain may be valid, but the blockchain containing double-spending may become longer than the blockchain containing normal transactions, so comparing lengths of the chain cannot completely prevent illegal transactions. In this paper, we propose an algorithm to detect double-spending and a mechanism to notify other nodes after detection. This algorithm is implemented and verified by using the bitcoin core.

Quality Adaptation Scheme based on VBR Content Characteristics to Improve QoE of UHD Streaming Service

Minsu Kim, Heekwang Kim, Kwangsue Chung

http://doi.org/10.5626/JOK.2018.45.8.856

With the development of networks and the spread of smart devices, the demand for UHD (Ultra High Definition) video is increasing, and HTTP Adaptive Streaming is attracting attention. The existing quality adaptation scheme has a problem, in that quality of experience (QoE) degrades because of bandwidth measurement that does not take into consideration VBR (Variable Bit Rate) content characteristics and quality selection using only measured bandwidth or buffer occupancy. In this paper, we propose a quality adaptation scheme based on VBR content characteristics to improve the QoE of UHD streaming service. The proposed scheme measures the bandwidth by considering the VBR content characteristics. The requested quality is selected based on the quality adaptation interval reflecting the change in the buffer occupancy, thereby increasing the average quality and minimizing unnecessary quality change. Experimental results show that the proposed scheme improves QoE with higher average quality and less quality change than do existing schemes.

Gender Recognition from Facial Sketch Images using Local Adaptive Structural Pattern

Md Tauhid Bin Iqbal, Oksam Chae

http://doi.org/10.5626/JOK.2018.45.8.866

In this paper, we present a new edge-based local image descriptor named Local Adaptive Structural Pattern (LASP), for the recognition of gender from facial sketch images. LASP generates eight directional edge responses of a pixel by applying Kirsch compass masks and selects top two directions to represent the local texture structure. Moreover, LASP applies an adaptivelyselected threshold on the top directional response in order to filter the low response of the flat pixels producing spurious codes. The top two Kirsch directions represent the local texture structure appropriately, whereas the imposed threshold on the top Kirsch-response differentiates the spurious codes generated from the flat regions, yielding a compact description of the facial sketches. We evaluate the performance of LASP in existing facial sketch datasets for the recognition of gender and observe improved accuracies compared to existing local descriptors.


Search




Journal of KIISE

  • ISSN : 2383-630X(Print)
  • ISSN : 2383-6296(Electronic)
  • KCI Accredited Journal

Editorial Office

  • Tel. +82-2-588-9240
  • Fax. +82-2-521-1352
  • E-mail. chwoo@kiise.or.kr