• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.6
• /
• pp.1325-1336
• /
• 2012

In the past about 10 different kinds of malicious code were found in one day on the average. However, the number of malicious codes that are found has rapidly increased reachingover 55,000 during the last 10 year. A large number of malicious codes, however, are not new kinds of malicious codes but most of them are new variants of the existing malicious codes as same functions are newly added into the existing malicious codes, or the existing malicious codes are modified to evade anti-virus detection. To deal with a lot of malicious codes including new malicious codes and variants of the existing malicious codes, we need to compare the malicious codes in the past and the similarity and classify the new malicious codes and the variants of the existing malicious codes. A former calculation method of the similarity on the existing malicious codes compare external factors of IPs, URLs, API, Strings, etc or source code levels. The former calculation method of the similarity takes time due to the number of malicious codes and comparable factors on the increase, and it leads to employing fuzzy hashing to reduce the amount of calculation. The existing fuzzy hashing, however, has some limitations, and it causes come problems to the former calculation of the similarity. Therefore, this research paper has suggested a new comparison method for malicious codes to improve performance of the calculation of the similarity using fuzzy hashing and also a classification method employing the new comparison method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.9
• /
• pp.2370-2387
• /
• 2012

A new security management model based on Rough set and Bayesian learner is proposed in the paper. The model focuses on finding out malicious nodes and getting them under control. The degree of dissatisfaction (DoD) is defined as the probability that a node belongs to the malicious node set. Based on transaction history records local DoD (LDoD) is calculated. And recommended DoD (RDoD) is calculated based on feedbacks on recommendations (FBRs). According to the DoD, nodes are classified and controlled. In order to improve computation accuracy and efficiency of the probability, we employ Rough set combined with Bayesian learner. For the reason that in some cases, the corresponding probability result can be determined according to only one or two attribute values, the Rough set module is used; And in other cases, the probability is computed by Bayesian learner. Compared with the existing trust model, the simulation results demonstrate that the model can obtain higher examination rate of malicious nodes and achieve the higher transaction success rate.

• Journal of the Korea Convergence Society
• /
• v.11 no.6
• /
• pp.23-28
• /
• 2020

A comment system is essential for communication on the Internet. However, there are also malicious comments such as inappropriate expression of others by exploiting anonymity online. In order to protect users from malicious comments, classification of malicious / normal comments is necessary, and this can be implemented as text classification. Text classification is one of the important topics in natural language processing, and studies using pre-trained models such as BERT and graph structures such as GCN and GAT have been actively conducted. In this study, we implemented a comment classification system using BERT, GCN, and GAT for actual published comments and compared the performance. In this study, the system using the graph-based model showed higher performance than the BERT.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.11
• /
• pp.85-93
• /
• 2018

In recent years, there has been an increasing number of ways to distribute document-based malicious code using vulnerabilities in document files. Because document type malware is not an executable file itself, it is easy to bypass existing security programs, so research on a model to detect it is necessary. In this study, we extract main features from the document structure and the JavaScript contained in the stream object In addition, when JavaScript is inserted, keywords with high occurrence frequency in malicious code such as function name, reserved word and the readable string in the script are extracted. Then, we generate a machine learning model that can distinguish between normal and malicious. In order to make it difficult to bypass, we try to achieve good performance in a black box type algorithm. For an experiment, a large amount of documents compared to previous studies is analyzed. Experimental results show 98.9% detection rate from three different type algorithms. SVM, which is a black box type algorithm and makes obfuscation difficult, shows much higher performance than in previous studies.

• ETRI Journal
• /
• v.43 no.3
• /
• pp.549-560
• /
• 2021

Cyberattacks are often difficult to identify with traditional signature-based detection, because attackers continually find ways to bypass the detection methods. Therefore, researchers have introduced artificial intelligence (AI) technology for cybersecurity analysis to detect malicious PowerShell scripts. In this paper, we propose a feature optimization technique for AI-based approaches to enhance the accuracy of malicious PowerShell script detection. We statically analyze the PowerShell script and preprocess it with a method based on the tokens and abstract syntax tree (AST) for feature selection. Here, tokens and AST represent the vocabulary and structure of the PowerShell script, respectively. Performance evaluations with optimized features yield detection rates of 98% in both machine learning (ML) and deep learning (DL) experiments. Among them, the ML model with the 3-gram of selected five tokens and the DL model with experiments based on the AST 3-gram deliver the best performance.

• Journal of Internet of Things and Convergence
• /
• v.9 no.6
• /
• pp.1-9
• /
• 2023

Malware files containing concealed malicious scripts have recently been identified within MS Office documents frequently. In response, this paper describes the design and implementation of a system that automatically detects malicious digital files using machine learning techniques. The system is proficient in identifying malicious scripts within MS Office files that exploit the OLE VBA macro functionality, detecting malicious scripts embedded within the CDH/LFH/ECDR internal field values through OOXML structure analysis, and recognizing abnormal CDH/LFH information introduced within the OOXML structure, which is not conventionally referenced. Furthermore, this paper presents a mechanism for utilizing the VirusTotal malicious script detection feature to autonomously determine instances of malicious tampering within MS Office files. This leads to the design and implementation of a machine learning-based integrated software. Experimental results confirm the software's capacity to autonomously assess MS Office file's integrity and provide enhanced detection performance for arbitrary MS Office files when employing the optimal machine learning model.

• Journal of Convergence Society for SMB
• /
• v.4 no.2
• /
• pp.13-18
• /
• 2014

Due to the development of information systems and the Internet, the Internet and smart phones can access networking in any where and any time. This causes the program to exploit various vulnerabilities and malicious code created to go out information, the disclosure of such crime increasing day by day. The proposed countermeasure model will be able to contribute to block all kinds of malicious code activities.

• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.101-106
• /
• 2023

Recently, cyberattacks are increasing in social engineering attacks using intelligent and continuous phishing sites and hacking techniques using malicious code. As personal security becomes important, there is a need for a method and a solution for determining whether a malicious URL exists using a web application. In this paper, we would like to find out each feature and limitation by comparing highly accurate techniques for detecting malicious URLs. Compared to classification algorithm models using features such as web flat panel DB and based URL detection sites, we propose an efficient URL anomaly detection technique.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3333-3354
• /
• 2022

The 5G Core Network (5GC) is an essential part of the mobile communication network, but its security protection strategy based on the boundary construction is difficult to ensure the security inside the network. For example, the Network Function (NF) mutual authentication mechanism that relies on the transport layer security mechanism and OAuth2.0's Client Credentials cannot identify the hijacked NF. To address this problem, this paper proposes a trust model for 5GC based on NF interaction behavior to identify malicious NFs and improve the inherent security of 5GC. First, based on the interaction behavior and context awareness of NF, the trust between NFs is quantified through the frequency ratio of interaction behavior and the success rate of interaction behavior. Second, introduce trust transmit to make NF comprehensively refer to the trust evaluation results of other NFs. Last, classify the possible malicious behavior of NF and define the corresponding punishment mechanism. The experimental results show that the trust value of NFs converges to stable values, and the proposed trust model can effectively evaluate the trustworthiness of NFs and quickly and accurately identify different types of malicious NFs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.454-475
• /
• 2018

This paper presents a novel Android malware classification model planned to classify and categorize Android malicious code at Drebin dataset. The amount of malicious mobile application targeting Android based smartphones has increased rapidly. In this paper, Restricted Boltzmann Machine and Deep Belief Network are used to classify malware into families of Android application. A texture-fingerprint based approach is proposed to extract or detect the feature of malware content. A malware has a unique "image texture" in feature spatial relations. The method uses information on texture image extracted from malicious or benign code, which are mapped to uncompressed gray-scale according to the texture image-based approach. By studying and extracting the implicit features of the API call from a large number of training samples, we get the original dynamic activity features sets. In order to improve the accuracy of classification algorithm on the features selection, on the basis of which, it combines the implicit features of the texture image and API call in malicious code, to train Restricted Boltzmann Machine and Back Propagation. In an evaluation with different malware and benign samples, the experimental results suggest that the usability of this method---using Deep Belief Network to classify Android malware by their texture images and API calls, it detects more than 94% of the malware with few false alarms. Which is higher than shallow machine learning algorithm clearly.