• Journal of Korea Multimedia Society
• /
• v.23 no.11
• /
• pp.1396-1405
• /
• 2020

Cyber threats such as forced personal information collection and distribution of malicious codes using malicious URLs continue to occur. In order to cope with such cyber threats, a security technologies that quickly detects malicious URLs and prevents damage are required. In a web environment, malicious URLs have various forms and are created and deleted from time to time, so there is a limit to the response as a method of detecting or filtering by signature matching. Recently, researches on detecting and predicting malicious URLs using machine learning techniques have been actively conducted. Existing studies have proposed various features and machine learning algorithms for predicting malicious URLs, but most of them are only suggesting specialized algorithms by supplementing features and preprocessing, so it is difficult to sufficiently reflect the strengths of various machine learning algorithms. In this paper, a system for predicting malicious URLs using multiple machine learning algorithms was proposed, and an experiment was performed to combine the prediction results of multiple machine learning models to increase the accuracy of predicting malicious URLs. Through experiments, it was proved that the combination of multiple models is useful in improving the prediction performance compared to a single model.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.149-156
• /
• 2022

Recently, there have been many reports of document-type malicious code injecting malicious code into Microsoft Office files. Document-type malicious code is often hidden by encoding the malicious code in the document. Therefore, document-type malware can easily bypass anti-virus programs. We found that malicious code was inserted into the Visual Basic for Applications (VBA) macro, a function supported by Microsoft Office. Malicious codes such as shellcodes that run external programs and URL-related codes that download files from external URLs were identified. We selected 354 keywords repeatedly appearing in malicious Microsoft Office files and defined the number of times each keyword appears in the body of the document as a feature. We performed machine learning with SVM, naïve Bayes, logistic regression, and random forest algorithms. As a result, each algorithm showed accuracies of 0.994, 0.659, 0.995, and 0.998, respectively.

• Convergence Security Journal
• /
• v.8 no.1
• /
• pp.49-56
• /
• 2008

Recently, Phising attack uses trick of URL and sites, and technical concealment method which infiltrates sophisticated malicious code. However, sometimes Phising security technology cannot cover all of Phising methods. Consequently, this research proposes inspection to solve this problem. First, we can install Proxy server for a strong open information exchange of web environment between web servers and clients. Therefore, it compares and analyzes harmful site and Phising URL with White domain list, and filters them. Finally, designs for stable web based information so that we can block Phising with least regulation and active control. So the purpose of this paper is introducing this design system and structure, and inspect them.

• Convergence Security Journal
• /
• v.15 no.1
• /
• pp.3-9
• /
• 2015

In this paper, a detection technique of smishing using a TaintDroid is suggested. Suggesting system detects malicious acts by transmitting a URL to the TaintDroid server and installing a relevant application to a virtual device of the TaintDroid server, when a smartphone user receives a text message including the URL suspected as a smishing. Through this we want to distinguish an application that can not install because of suspicion of a smishing in an actual smartphone whether said application is malicious application or not by testing with the virtual device of said system. The detection technique of a smishing using the TaintDroid suggested in this paper is possible to detect in a new form a smishing with a text message and to identifying which application it is through analysis of results from a user.

• Journal of Platform Technology
• /
• v.9 no.3
• /
• pp.3-17
• /
• 2021

Advanced persistent threat (APT) attacks are attacks aimed at a particular entity as a set of latent and persistent computer hacking processes. These APT attacks are usually carried out through various methods, including spam mail and disguised banner advertising. The same name is also used for files, since most of them are distributed via spam mail disguised as invoices, shipment documents, and purchase orders. In addition, such Infostealer attacks were the most frequently discovered malicious code in the first week of February 2021. CDR is a 'Content Disarm & Reconstruction' technology that can prevent the risk of malware infection by removing potential security threats from files and recombining them into safe files. Gartner, a global IT advisory organization, recommends CDR as a solution to attacks in the form of attachments. There is a program using CDR techniques released as open source is called 'Dangerzone'. The program supports the extension of most document files, but does not support the extension of HWP files that are widely used in Korea. In addition, Gmail blocks malicious URLs first, but it does not block malicious URLs in mail systems such as Naver and Daum, so malicious URLs can be easily distributed. Based on this problem, we developed a 'Dangerzone' program that supports the HWP extension to prevent APT attacks, and a Chrome extension that performs URL checking in Naver and Daum mail and blocking banner ads.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.6
• /
• pp.1185-1195
• /
• 2014

Domestic and international CERTs are carrying out security monitoring and response services based on security devices for intrusion incident prevention and damage minimization of the organizations. However, the security monitoring and response service has a fatal limitation in that it is unable to detect unknown attacks that are not matched to the predefined signatures. In recent, many approaches have adopted the darknet technique in order to overcome the limitation. Since the darknet means a set of unused IP addresses, no real systems connected to the darknet. Thus, all the incoming traffic to the darknet can be regarded as attack activities. In this paper, we present a collection and analysis method of malicious URLs based on darkent traffic for advanced security monitoring and response service. The proposed method prepared 8,192 darknet space and extracted all of URLs from the darknet traffic, and carried out in-depth analysis for the extracted URLs. The analysis results can contribute to the emergence response of large-scale cyber threats and it is able to improve the performance of the security monitoring and response if we apply the malicious URLs into the security devices, DNS sinkhole service, etc.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.672-678
• /
• 2021

New malware continues to increase and become advanced by every year. Although various studies are going on executable files to diagnose malicious codes, it is difficult to detect attacks that internalize malicious code threats in emails by exploiting non-executable document files, malicious URLs, and malicious macros and JS in documents. In this paper, we introduce a method of analyzing malicious code for email security through proactive detection and blocking of malicious email attacks, and propose a method for determining whether a non-executable document file is malicious based on AI. Among various algorithms, an efficient machine learning modeling is choosed, and an ML workflow system to diagnose malicious code using Kubeflow is proposed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.7
• /
• pp.1290-1295
• /
• 2016

Recently, as mobile internet usage has been increasing rapidly, malware attacks through user's web browsers has been spreading in a way of social engineering or drive-by downloading. Existing defense mechanism against drive-by download attack mainly focused on final download sites and distribution paths. However, detection and prevention of injection sites to inject malicious code into the comprised websites have not been fully investigated. In this paper, for the purpose of improving defense mechanisms against these malware downloads attacks, we focus on detecting the injection site which is the key source of malware downloads spreading. As a result, in addition to the current URL blacklist techniques, we proposed the enhanced method which adds features of detecting the injection site to prevent the malware spreading. We empirically show that the proposed method can effectively minimize malware infections by blocking the source of the infection spreading, compared to other approaches of the URL blacklisting that directly uses the drive-by browser exploits.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.699-700
• /
• 2011

This paper shows the way to prevent the leaking of private information due to malicious codes or connections of invalid URL in QR-Codes, which is used in the present smart-phone. It is difficult to filter out the connections directly with decoding the QR-Codes, so before connecting, we construct servers which compare results of decoding the QR-Codes to a valid URL. The server notifies warning to Smart-phone users if the results were uncertain URLs which did not registered in the server. This paper would help the Smart-phone users to protect their privacy.

• Journal of Computing Science and Engineering
• /
• v.6 no.3
• /
• pp.179-192
• /
• 2012

This paper presents novel statistical algorithms for protecting the iTrust information retrieval network against malicious attacks. In iTrust, metadata describing documents, and requests containing keywords, are randomly distributed to multiple participating nodes. The nodes that receive the requests try to match the keywords in the requests with the metadata they hold. If a node finds a match, the matching node returns the URL of the associated information to the requesting node. The requesting node then uses the URL to retrieve the information from the source node. The novel detection algorithm determines empirically the probabilities of the specific number of matches based on the number of responses that the requesting node receives. It also calculates the analytical probabilities of the specific numbers of matches. It compares the observed and the analytical probabilities to estimate the proportion of subverted or non-operational nodes in the iTrust network using a window-based method and the chi-squared statistic. If the detection algorithm determines that some of the nodes in the iTrust network are subverted or non-operational, then the novel defensive adaptation algorithm increases the number of nodes to which the requests are distributed to maintain the same probability of a match when some of the nodes are subverted or non-operational as compared to when all of the nodes are operational. Experimental results substantiate the effectiveness of the detection and defensive adaptation algorithms for protecting the iTrust information retrieval network against malicious attacks.