arXiv subjects

Sang-Wook Kim

Publications and source records attributed to Sang-Wook Kim.

26 records · Page 2Linked to original sources

arXiv2022

Phishing URL Detection: A Network-based Approach Robust to Evasion

Many cyberattacks start with disseminating phishing URLs. When clicking these phishing URLs, the victim's private information is leaked to the attacker. There have been proposed several machine learning methods to detect phishing URLs. However, it still remains under-explored to detect phishing URLs with evasion, i.e., phishing URLs that pretend to be benign by manipulating patterns. In many cases, the attacker i) reuses prepared phishing web pages because making a completely brand-new set costs non-trivial expenses, ii) prefers hosting companies that do not require private information and are cheaper than others, iii) prefers shared hosting for cost efficiency, and iv) sometimes uses benign domains, IP addresses, and URL string patterns to evade existing detection methods. Inspired by those behavioral characteristics, we present a network-based inference method to accurately detect phishing URLs camouflaged with legitimate patterns, i.e., robust to evasion. In the network approach, a phishing URL will be still identified as phishy even after evasion unless a majority of its neighbors in the network are evaded at the same time. Our method consistently shows better detection performance throughout various experimental tests than state-of-the-art methods, e.g., F-1 of 0.89 for our method vs. 0.84 for the best feature-based method.

cs.CR↗

arXiv2021

Linear, or Non-Linear, That is the Question!

There were fierce debates on whether the non-linear embedding propagation of GCNs is appropriate to GCN-based recommender systems. It was recently found that the linear embedding propagation shows better accuracy than the non-linear embedding propagation. Since this phenomenon was discovered especially in recommender systems, it is required that we carefully analyze the linearity and non-linearity issue. In this work, therefore, we revisit the issues of i) which of the linear or non-linear propagation is better and ii) which factors of users/items decide the linearity/non-linearity of the embedding propagation. We propose a novel Hybrid Method of Linear and non-linEar collaborative filTering method (HMLET, pronounced as Hamlet). In our design, there exist both linear and non-linear propagation steps, when processing each user or item node, and our gating module chooses one of them, which results in a hybrid model of the linear and non-linear GCN-based collaborative filtering (CF). The proposed model yields the best accuracy in three public benchmark datasets. Moreover, we classify users/items into the following three classes depending on our gating modules' selections: Full-Non-Linearity (FNL), Partial-Non-Linearity (PNL), and Full-Linearity (FL). We found that there exist strong correlations between nodes' centrality and their class membership, i.e., important user/item nodes exhibit more preferences towards the non-linearity during the propagation steps. To our knowledge, we are the first who design a hybrid method and report the correlation between the graph centrality and the linearity/non-linearity of nodes. All HMLET codes and datasets are available at: https://github.com/qbxlvnf11/HMLET.

cs.IR↗

arXiv2019

Creating A Neural Pedagogical Agent by Jointly Learning to Review and Assess

Machine learning plays an increasing role in intelligent tutoring systems as both the amount of data available and specialization among students grow. Nowadays, these systems are frequently deployed on mobile applications. Users on such mobile education platforms are dynamic, frequently being added, accessing the application with varying levels of focus, and changing while using the service. The education material itself, on the other hand, is often static and is an exhaustible resource whose use in tasks such as problem recommendation must be optimized. The ability to update user models with respect to educational material in real-time is thus essential; however, existing approaches require time-consuming re-training of user features whenever new data is added. In this paper, we introduce a neural pedagogical agent for real-time user modeling in the task of predicting user response correctness, a central task for mobile education applications. Our model, inspired by work in natural language processing on sequence modeling and machine translation, updates user features in real-time via bidirectional recurrent neural networks with an attention mechanism over embedded question-response pairs. We experiment on the mobile education application SantaTOEIC, which has 559k users, 66M response data points as well as a set of 10k study problems each expert-annotated with topic tags and gathered since 2016. Our model outperforms existing approaches over several metrics in predicting user response correctness, notably out-performing other methods on new users without large question-response histories. Additionally, our attention mechanism and annotated tag set allow us to create an interpretable education platform, with a smart review system that addresses the aforementioned issue of varied user attention and problem exhaustion.

cs.LG↗

arXiv2019

Clustering-Based Collaborative Filtering Using an Incentivized/Penalized User Model

Giving or recommending appropriate content based on the quality of experience is the most important and challenging issue in recommender systems. As collaborative filtering (CF) is one of the most prominent and popular techniques used for recommender systems, we propose a new clustering-based CF (CBCF) method using an incentivized/penalized user (IPU) model only with ratings given by users, which is thus easy to implement. We aim to design such a simple clustering-based approach with no further prior information while improving the recommendation accuracy. To be precise, the purpose of CBCF with the IPU model is to improve recommendation performance such as precision, recall, and $F_1$ score by carefully exploiting different preferences among users. Specifically, we formulate a constrained optimization problem, in which we aim to maximize the recall (or equivalently $F_1$ score) for a given precision. To this end, users are divided into several clusters based on the actual rating data and Pearson correlation coefficient. Afterwards, we give each item an incentive/penalty according to the preference tendency by users within the same cluster. Our experimental results show a significant performance improvement over the baseline CF scheme without clustering in terms of recall or $F_1$ score for a given precision.

cs.IR↗

arXiv2011

C-Rank: A Link-based Similarity Measure for Scientific Literature Databases

As the number of people who use scientific literature databases grows, the demand for literature retrieval services has been steadily increased. One of the most popular retrieval services is to find a set of papers similar to the paper under consideration, which requires a measure that computes similarities between papers. Scientific literature databases exhibit two interesting characteristics that are different from general databases. First, the papers cited by old papers are often not included in the database due to technical and economic reasons. Second, since a paper references the papers published before it, few papers cite recently-published papers. These two characteristics cause all existing similarity measures to fail in at least one of the following cases: (1) measuring the similarity between old, but similar papers, (2) measuring the similarity between recent, but similar papers, and (3) measuring the similarity between two similar papers: one old, the other recent. In this paper, we propose a new link-based similarity measure called C-Rank, which uses both in-link and out-link by disregarding the direction of references. In addition, we discuss the most suitable normalization method for scientific literature databases and propose an evaluation method for measuring the accuracy of similarity measures. We have used a database with real-world papers from DBLP and their reference information crawled from Libra for experiments and compared the performance of C-Rank with those of existing similarity measures. Experimental results show that C-Rank achieves a higher accuracy than existing similarity measures.

cs.DL↗

arXiv2011

A Community-Based Sampling Method Using DPL for Online Social Network

In this paper, we propose a new graph sampling method for online social networks that achieves the following. First, a sample graph should reflect the ratio between the number of nodes and the number of edges of the original graph. Second, a sample graph should reflect the topology of the original graph. Third, sample graphs should be consistent with each other when they are sampled from the same original graph. The proposed method employs two techniques: hierarchical community extraction and densification power law. The proposed method partitions the original graph into a set of communities to preserve the topology of the original graph. It also uses the densification power law which captures the ratio between the number of nodes and the number of edges in online social networks. In experiments, we use several real-world online social networks, create sample graphs using the existing methods and ours, and analyze the differences between the sample graph by each sampling method and the original graph.

cs.SI↗

arXiv2011

A Linear-Time Approximation of the Earth Mover's Distance

Color descriptors are one of the important features used in content-based image retrieval. The Dominant Color Descriptor (DCD) represents a few perceptually dominant colors in an image through color quantization. For image retrieval based on DCD, the earth mover's distance and the optimal color composition distance are proposed to measure the dissimilarity between two images. Although providing good retrieval results, both methods are too time-consuming to be used in a large image database. To solve the problem, we propose a new distance function that calculates an approximate earth mover's distance in linear time. To calculate the dissimilarity in linear time, the proposed approach employs the space-filling curve for multidimensional color space. To improve the accuracy, the proposed approach uses multiple curves and adjusts the color positions. As a result, our approach achieves order-of-magnitude time improvement but incurs small errors. We have performed extensive experiments to show the effectiveness and efficiency of the proposed approach. The results reveal that our approach achieves almost the same results with the EMD in linear time.

cs.IR↗

arXiv2006

Development of deformation-tunable quadrupolar microcavity

We have developed a technique for realizing a two-dimensional quadrupolar microcavity with its deformation variable from 0% to 20% continuously. We employed a microjet ejected from a noncircular orifice in order to generate a stationary column with modulated quadrupolar deformation in its cross section. Wavelength red shifts of low-order cavity modes due to shape deformation were measured and were found to be in good agreement with the wave calculation for the same deformation, indicating the observed deformation is quadrupolar in nature.

physics.optics↗