• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.4008-4023
• /
• 2022

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.438-449
• /
• 2018

Recently, various graph data have been utilized in various fields such as social networks and citation networks. As the graph changes dynamically over time, it is necessary to manage the graph historical data for tracking changes and retrieving point-in-time graphs. Most historical data changes partially according to time, so unchanged data is stored redundantly when data is stored in units of time. In this paper, we propose a graph history storage management method to minimize the redundant storage of time graphs. The proposed method continuously detects the change of the graph and stores the overlapping subgraph in intersection snapshot. Intersection snapshots are connected by a number of delta snapshots to maintain change data over time. It improves space efficiency by collectively managing overlapping data stored in intersection snapshots. We also linked intersection snapshots and delta snapshots to retrieval the graph at that point in time. Various performance evaluations are performed to show the superiority of the proposed scheme.

• International Journal of Contents
• /
• v.10 no.1
• /
• pp.23-28
• /
• 2014

When developing a classifier using various objective functions, it is important to compare the performances of the classifiers. Although there are statistical analyses of objective functions for classifiers, simulation results can provide us with direct comparison results and in this case, a comparison criterion is considerably critical. A Receiver Operating Characteristics (ROC) graph is a simulation technique for comparing classifiers and selecting a better one based on a performance. In this paper, we adopt the ROC graph to compare classifiers trained by mean-squared error, cross-entropy error, classification figure of merit, and the n-th order extension of cross-entropy error functions. After the training of feed-forward neural networks using the CEDAR database, the ROC graphs are plotted to help us identify which objective function is better.

• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1158-1167
• /
• 2017

Many real-world applications information are organized and represented with graph structure which is often used for representing various ubiquitous networks, such as World Wide Web, social networks, and protein-protein interactive networks. In particular, similarity evaluation between graphs is a challenging issue in many fields such as graph searching, pattern discovery, neuroscience, chemical compounds exploration and so forth. There exist some algorithms which are based on vertices or edges properties, are proposed for addressing this issue. However, these algorithms do not take both vertices and edges similarities into account. Towards this end, this paper pioneers a novel approach for similarity evaluation between graphs based on formal concept analysis. The feature of this approach is able to characterize the relationships between nodes and further reveal the similarity between graphs. Therefore, the highlight of our approach is to take vertices and edges into account simultaneously. The proposed algorithm is evaluated using a case study for validating the effectiveness of the proposed approach on detecting and measuring the similarity between graphs.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1643-1652
• /
• 2022

Most of the existing machine reading research has used Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) algorithms as networks. Among them, RNN was slow in training, and Question Answering Network (QANet) was announced to improve training speed. QANet is a model composed of CNN and self-attention. CNN extracts semantic and syntactic information well from the local corpus, but there is a limit to extracting the corresponding information from the global corpus. Graph Convolutional Networks (GCN) extracts semantic and syntactic information relatively well from the global corpus. In this paper, to take advantage of this strength of GCN, we propose I-QANet, which changed the CNN of QANet to GCN. The proposed model performed 1.2 times faster than the baseline in the Stanford Question Answering Dataset (SQuAD) dataset and showed 0.2% higher performance in Exact Match (EM) and 0.7% higher in F1. Furthermore, in the Korean Question Answering Dataset (KorQuAD) dataset consisting only of Korean, the learning time was 1.1 times faster than the baseline, and the EM and F1 performance were also 0.9% and 0.7% higher, respectively.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.22-24
• /
• 2021

This paper is a proposal for edge weight prediction using neural networks to graph configurations of nodes and edges. Brand is one of the components of society. and one of the brand's most important strategies is geographical location strategy. This paper is focus on that strategy. In This paper propose two things: 1) Graph Configuration. node consists of brand store, edge consists of store-to-store relationships and edge weight consists of actual walk and drive distance values. 2) numbering edges and training neural networks to predict next store distance values. It is expected to be useful in analyzing successful brand geographical location strategies.

• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1250-1260
• /
• 2020

This study proposes a novel deep neural network model that can accurately detect objects and their relationships in an image and represent them as a scene graph. The proposed model utilizes several multimodal features, including linguistic features and visual context features, to accurately detect objects and relationships. In addition, in the proposed model, context features are embedded using graph neural networks to depict the dependencies between two related objects in the context feature vector. This study demonstrates the effectiveness of the proposed model through comparative experiments using the Visual Genome benchmark dataset.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.471-476
• /
• 2024

With the spread of various smart devices and computing devices, big data generation is occurring widely. Machine learning is an algorithm that performs reasoning by learning data patterns. Among the various machine learning algorithms, the algorithm that attracts attention is deep learning based on neural networks. Deep learning is achieving rapid performance improvement with the release of various applications. Recently, among deep learning algorithms, attempts to analyze data using graph structures are increasing. In this study, we present a graph generation method for transferring to a deep learning network. This paper proposes a method of generalizing node properties and edge weights in the graph generation process and converting them into a structure for deep learning input by presenting a matricization We present a method of applying a linear transformation matrix that can preserve attribute and weight information in the graph generation process. Finally, we present a deep learning input structure of a general graph and present an approach for performance analysis.

• Journal of Information Processing Systems
• /
• v.7 no.1
• /
• pp.75-84
• /
• 2011

The enhanced pyramid graph was recently proposed as an interconnection network model in parallel processing for maximizing regularity in pyramid networks. We prove that there are two edge-disjoint Hamiltonian cycles in the enhanced pyramid networks. This investigation demonstrates its superior property in edge fault tolerance. This result is optimal in the sense that the minimum degree of the graph is only four.

• Journal of Korea Multimedia Society
• /
• v.5 no.1
• /
• pp.114-119
• /
• 2002

Realtime assignment of railways is an important component in the railway control systems. To solve this problem, we must exactly represent the track topology. Graph is a proper data structure for representing general network topologies, but not Proper for track topologies. In this paper, we define a new data structure, railway graph, which can exactly represent topologies of railway networks. And we describe a path search algorithm in the defined railway graph, and a top-down approach for designing railway network by the Proposed graph.