• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.451-461
• /
• 2021

As various smart devices spread and the damage caused by malicious codes becomes more serious, malicious code detection technology using machine learning technology is attracting attention. However, if the training data of machine learning is constructed based on only the fragmentary characteristics of the code, it is still easy to create variants and new malicious codes that avoid it. To solve such a problem, a research using the function call relationship of malicious code as training data is attracting attention. In particular, it is expected that more advanced malware detection will be possible by measuring the similarity of graphs using GNN. This paper proposes an efficient method to generate a function call graph from binary code to utilize GNN for malware detection.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.593-603
• /
• 2020

The advent of malicious code has increased exponentially due to the spread of malicious code generation tools in accordance with the development of the network, but there is a limit to the response through existing malicious code detection methods. According to this situation, a machine learning-based malicious code detection method is evolving, and in this paper, the feature of data is extracted from the PE header for machine-learning-based malicious code detection, and then it is used to automate the malware through autoencoder. Research on how to extract the indicated features and feature importance. In this paper, 549 features composed of information such as DLL/API that can be identified from PE files that are commonly used in malware analysis are extracted, and autoencoder is used through the extracted features to improve the performance of malware detection in machine learning. It was proved to be successful in providing excellent accuracy and reducing the processing time by 2 times by effectively extracting the features of the data by compressively storing the data. The test results have been shown to be useful for classifying malware groups, and in the future, a classifier such as SVM will be introduced to continue research for more accurate malware detection.

• Journal of KIISE
• /
• v.41 no.10
• /
• pp.859-869
• /
• 2014

In recent years, the obfuscation techniques are commonly exploited to protect malwares, so obfuscated malwares have become a big threat. Especially, it is extremely hard to analyze virtualization-obfuscated malwares based on unusual virtual machines, because the original program is hidden by the virtual machine as well as its semantics is mixed with the semantics of the virtual machine. To confront this threat, we suggest a framework to analyze virtualization-obfuscated programs based on the dynamic analysis. First, we extract the dynamic execution trace of the virtualization-obfuscated executables. Second, we analyze the traces by translating machine instruction sequences into the intermediate representation and extract the virtual machine architecture by constructing dynamic context flow graphs. Finally, we extract abstract semantics of the original program using the extracted virtual machine architecture. In this paper, we propose a method to extract the information of the original program from a virtualization-obfuscated program by some commercial obfuscation tools. We expect that our tool can be used to understand virtualization-obfuscated programs and integrate other program analysis techniques so that it can be applied to analysis of the semantics of original programs using the abstract semantics.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.23 no.4
• /
• pp.709-720
• /
• 2013

Virtualization obfuscation makes hard to analyze the code by applying virtualization to code section. Protected code by common used virtualization obfuscation technique has become known that it doesn't have restored point and also it is hard to analyze. However, it is abused to protect malware recently. So, It is been hard to analyze and take action for malware. Therefore, this paper's purpose is analyze and take action for protected malware by virtualization obfuscation technique through implement tool which can extract virtualization structure automatically and trace execution process. Hence, basic structure and operation process of virtualization obfuscation technique will be handled and analysis result of protected malware by virtualization obfuscation utilized Equation Reasoning System, one kind of program analysis. Also, we implement automatic analysis tool, extract virtualization structure from protected executable file by virtualization obfuscation technique and deduct program's execution sequence.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.279-281
• /
• 2018

랜섬웨어는 사용자의 중요 파일을 암호화한 후 금전을 요구하는 형태의 악성코드로, 전 세계적으로 큰 피해를 발생시켰다. 안드로이드 환경에서의 랜섬웨어는 앱을 통해 동작하기 때문에, 앱의 악의적인 암호화 기능 수행을 실시간으로 탐지할 수 있는 방안에 대한 연구들이 진행되고 있다. 자원 제한적인 안드로이드 환경에서 중요한 파일들에 대한 암호화 수행 여부를 실시간으로 탐지하기 위한 방안으로 Shannon 엔트로피 값 비교가 있다. 하지만 파일의 종류에 따라 Shannon 엔트로피 값이 크게 달라질 수 있으며, 암호화 기능 수행에 대한 오탐이 발생할 수 있다. 따라서 본 논문에서는 파일에 대한 분할된 Shannon 엔트로피 값을 측정하여 암호화 기능 수행 탐지의 정확성을 높이고자 한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.5
• /
• pp.1019-1026
• /
• 2019

Due to limitations of existing methods for detecting newly introduced malware, the importance of the development of artificial intelligence vaccines arises. Existing artificial intelligence vaccines have a disadvantage that the accuracy of the detection rate is low because those vaccines do not scan all parts of the file. In this paper, we suggest an enhanced method for detecting malware which is composed of unique OP Code features in the malware files. Specifically, we tested the method with text datasets trained on Random Forest algorithm and with image datasets trained on the Inception V3 model. As a result, the highest accuracy of the detection rate was about 80%.

• Journal of the Korea Convergence Society
• /
• v.8 no.3
• /
• pp.49-61
• /
• 2017

Recently, convenience and usability are increasing with the development and deployment of various mobile applications on the Android platform. However, important information stored in the smartphone is leaked to the outside without knowing the user since the malicious mobile application is continuously increasing. A variety of mobile vaccines have been developed for the Android platform to detect malicious apps. Recently discovered server-based polymorphic(SSP) malicious mobile apps include obfuscation techniques. Therefore, it is not easy to detect existing mobile vaccines because some other form of malicious app is newly created by using SSP mechanism. In this paper, we analyze the correlation between the similarity of the method in the DEX file constituting the core malicious code and the permission similarity measure through APK de-compiling process for the SSP malicious app. According to the analysis results of DEX method similarity and permission similarity, we could extract the characteristics of SSP malicious apps and found the difference that can be distinguished from the normal app.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.945-954
• /
• 2022

Billions of malicious codes are detected every year, of which only 0.01% are new types of malware. In this situation, an effective malware type classification tool is needed, but previous studies have limitations in quickly analyzing a large amount of malicious code because it requires a complex and massive amount of data pre-processing. To solve this problem, this paper proposes a method to classify the types of malicious code based on the similarity hash without complex data preprocessing. This approach trains the XGBoost model based on the similarity hash information of the malware. To evaluate this approach, we used the BIG-15 dataset, which is widely used in the field of malware classification. As a result, the malicious code was classified with an accuracy of 98.9% also, identified 3,432 benign files with 100% accuracy. This result is superior to most recent studies using complex preprocessing and deep learning models. Therefore, it is expected that more efficient malware classification is possible using the proposed approach.

• Information and Communications Magazine
• /
• v.29 no.8
• /
• pp.65-71
• /
• 2012

스마트폰을 비롯한 다양한 모바일 기기 보급이 급속도로 증가하고 있고, 이들 기기에 저장된 각종 개인정보에 대한 불법적 접근을 노라는 악성 앱들로 인한 피해가 발생하고 있다. 이들 위변조 앱 출현의 원인 중의 하나는 앱 실행화일의 역컴파일이 쉽기 때문이다. 앱 역컴파일이 쉽게 이루어지지 않도록 하기 위한 기술 중의 하나가 코드 난독화 기술이다. 따라서, 본 고에서는 일반적인 난독화 기술들을 분류하고, 현존하는 안드로이드, 아이폰, 윈도폰에 적용가능한 난독화 도구들의 기능에 대하여 조사 분석한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.21-28
• /
• 2016

File Time information has a significant meaning in digital forensic investigation. File time information in Linux Ext4 (Extended File System 4) environment is the Access Time, Modification Time, Inode Change Time, Deletion Time and Creation Time. File time is variously changed by user manipulations such as creation, copy and edit. And, the study of file time change is necessary for evidence analysis. This study analyzes the change in time information of files or folders resulting from user manipulations in Linux operating system and analyzes ways to determine real time of malware infection and whether the file was modulation.