JHJiwon Hong

Jiwon Hong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jiwon Hong has a total of 32 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    C-Affinity: A Novel Similarity Measure for Effective Data Clustering

    by Jiwon Hong, Sang-Wook Kim

    Clustering is widely employed in various applications as it is one of the most useful data mining techniques. In performing clustering, a similarity measure, which defines how similar a pair of data objects are, plays an important role. A similarity measure is employed by considering a target dataset’s characteristics. Current similarity measures (or distances) do not reflect the distribution of data objects in a dataset at all. From the clustering point of view, this fact may limit the clustering accuracy. In this paper, we propose c-affinity, a new notion of a similarity measure that reflects the distribution of objects in the given dataset from a clustering point of view. We design c-affinity between any two objects to have a higher value as they are more likely to belong to the same cluster by learning the data distribution. We use random walk with restart (RWR) on the k-nearest neighbor graph of the given dataset to measure (1) how similar a pair of objects are and (2) how densely other objects are distributed between them. Via extensive experiments on sixteen synthetic and real-world datasets, we verify that replacing the existing similarity measure with our c-affinity improves the clustering accuracy significantly.


  • Open Access

    Classifying Malicious Documents on the Basis of Plain-Text Features: Problem, Solution, and Experiences

    by Jiwon Hong, Dongho Jeong, Sang-Wook Kim

    Cyberattacks widely occur by using malicious documents. A malicious document is an electronic document containing malicious codes along with some plain-text data that is human-readable. In this paper, we propose a novel framework that takes advantage of such plaintext data to determine whether a given document is malicious. We extracted plaintext features from the corpus of electronic documents and utilized them to train a classification model for detecting malicious documents. Our extensive experimental results with different combinations of three well-known vectorization strategies and three popular classification methods on five types of electronic documents demonstrate that our framework provides high prediction accuracy in detecting malicious documents.


  • Open Access

    Identifying the Author Group of Malwares through Graph Embedding and Human-in-the-Loop Classification

    by Dong-Kyu Chae, Sung-Jun Park, Eujeanne Kim, Jiwon Hong, Sang-Wook Kim

    Malware are developed for various types of malicious attacks, e.g., to gain access to a user’s private information or control of the computer system. The identification and classification of malware has been extensively studied in academic societies and many companies. Beyond the traditional research areas in this field, including malware detection, malware propagation analysis, and malware family clustering, this paper focuses on identifying the “author group” of a given malware as a means of effective detection and prevention of further malware threats, along with providing evidence for proper legal action. Our framework consists of a malware-feature bipartite graph construction, malware embedding based on DeepWalk, and classification of the target malware based on the k-nearest neighbors (KNN) classification. However, our KNN classifier often faced ambiguous cases, where it should say “I don’t know” rather than attempting to predict something with a high risk of misclassification. Therefore, our framework allows human experts to intervene in the process of classification for the final decision. We also developed a graphical user interface that provides the points of ambiguity for helping human experts to effectively determine the author group of the target malware. We demonstrated the effectiveness of our human-in-the-loop classification framework via extensive experiments using real-world malware data.


  • Open Access

    TrustRec: An effective approach to exploit implicit trust and distrust relationships along with explicitones for accurate recommendations

    by Reyhani Masoud Hamedani, Irfan Ali, Jiwon Hong, Sang-Wook Kim

    Trust-aware recommendation approaches are widely used to mitigate the cold-start problem in recommender systems by utilizing trust networks. In this paper, we point out the problems of existing trust-aware recommendation approaches as follows: (P1) exploiting sparse explicit trust and distrust relationships; (P2) considering a misleading assumption that a user pair having a trust/distrust relationship certainly has a similar/dissimilar preference in practice; (P3) employing the transitivity of distrust relationships. Then, we propose TrustRec, a novel approach based on the matrix factorization that provides an effective solution to each of the aforementioned problems and incorporates all of them in a single matrix factorization model. Furthermore, TrustRec exploits only top-k most similar trustees and dissimilar distrustees of each user to improve both the computational cost and accuracy. The results of our extensive experiments demonstrate that TructRec outperforms existing approaches in terms of both effectiveness and efficiency.


  • Open Access

    An Effective Approach to Outlier Detection Based on Centrality and Centre-Proximity

    by Duck-Ho Bae, Seo Jeong, Jiwon Hong, Minsoo Lee, Mirjana Ivanović, Miloš Savić, Sang-Wook Kim

    Publisher: Vilnius University Institute of Data Science and Digital Technologies, Journal: Informatica, Title: An Effective Approach to Outlier Detection Based on Centrality and Centre-Proximity, Authors: Duck-Ho Bae, Seo Jeong, Jiwon Hong, Minsoo Lee, Mirjana Ivanović, Miloš Savić, Sang-Wook Kim , In data mining research, outliers usually represent extreme values that deviate from other observations on data. The significant issue of existing outlier detection methods is that they only consider the object itself not taking its neighbouring objects into account to extract location features. In this paper, we propose an innovative approach to this issue. First, we propose the notions of centrality and centre-proximity for determining the degree of outlierness considering the distribution of all objects. We also propose a novel graph-based algorithm for outlier detection based on the notions. The algorithm solves the problems of existing methods, i.e. the problems of local density, micro-cluster, and fringe objects. We performed extensive experiments in order to confirm the effectiveness and efficiency of our proposed method. The obtained experimental results showed that the proposed method uncovers outliers successfully, and outperforms previous outlier detection methods.


  • Exploiting job transition patterns for effective job recommendation

    by Yujin Lee, Yeon-Chang Lee, Jiwon Hong, Sang-Wook Kim

    E-recruitment sites such as LinkedIn, Reed, and Indeed have a huge number of professional resumes from job seekers and job openings posted by recruiters. In this situation, it is a very time-consuming task for job seekers to find job openings that are well matched to their careers and desired conditions. Accordingly, active studies on job recommendation (JR) have been conducted recently. In this paper, we address the important property of transition patterns in JR that previous studies have overlooked. To incorporate the property into JR, we first propose two data modeling methods of adjacent pairing and all paring that represent a career path of a job seeker as a set of job pairs. Then, we propose frequency-based and graph-based methods of preference inference based on the data modeling methods. Finally, we develop four recommendation approaches, AdjacentFreq, AllFreq, AdjacentGraph, and AllGraph, each of which is a combination of two data modeling methods and two preference inference methods. Through extensive experiments using a real-life dataset, we show that our proposed approaches effectively address the unique property of JR. Also, we show that JR utilizing the transition information provides accuracy higher than JR not using the information.


  • Open Access

    An Accurate, Efficient, and Scalable Approach to Channel Matching in Smart TVs

    by Jiwon Hong, Sang-Wook Kim, Mina Rho, YoonHee Choi, Yoonsik Tak

    Smart TVs are rapidly replacing conventional TVs. In a number of countries, set-top boxes (STB) are widely used to relay TV channels to smart TVs. In such cases, smart TVs cannot identify which TV channel they are receiving. This situation makes it challenging for smart TVs to provide their users with a variety of personalized services, such as context-aware services and recommendation services. In this paper, we introduce our TV channel matching system that resolves such problems. We propose strategies for scaling-out the matching system and improving its accuracy.

  • Classifying malwares for identification of author groups

    by Jiwon Hong, Sanghyun Park, Sang‐Wook Kim, Dongphil Kim, Wonho Kim

    Summary: Malwares are growing exponentially in number, and authors of malwares are continuously releasing new ones. Malwares developed by the same author group might have similar signatures. For a number of applications including digital forensic and law enforcement, such characteristics can be used to determine which author group is likely to have released a given malware. In this paper, we describe a new type of classification that identifies which group of authors is most likely to have developed a given malware. We identify and verify a set of various features obtained through static and dynamic analyses of malwares and exploit them for classification. We evaluate our approach through extensive experiments with a real‐world dataset labeled by a group of domain experts. The results show that our approach is effective and provides good accuracy in malware classification.


  • Open Access

    Exploiting implicit and explicit signed trust relationships for effective recommendations

    by Irfan Ali, Jiwon Hong, Sang-Wook Kim

    Trust networks have been widely used to mitigate the data sparsity and cold-start problems of collaborative filtering. Recently, some approaches have been proposed which exploit explicit signed trust relationships, i.e., trust and distrust relationships. These approaches ignore the fact that users despite trusting/distrusting each other in a trust network may have different preferences in real-life. Most of these approaches also handle the notion of the transitivity of distrust as well as trust. However, other existing work observed that trust is transitive while distrust is intransitive. Moreover, explicit signed trust relationships are fairly sparse and may not contribute to infer true preferences of users. In this paper, we propose to create implicit signed trust relationships and exploit them along with explicit signed trust relationship to solve sparsity problem of trust relationships. We also confirm the similarity (resp. dissimilarity) of implicit and explicit trust (resp. distrust) relationships by using the similarity score between users so that users' true preferences can be inferred. In addition to these strategies, we also propose a matrix factorization model that simultaneously exploits implicit and explicit signed trust relationships along with rating information and also handles transitivity of trust and intransitivity of distrust. Extensive experiments on Epinions dataset show that the proposed approach outperforms existing approaches in terms of accuracy.