[논문]블록체인과 딥러닝을 이용한 악성코드 탐지에 관한 연구

이덕규

doi:10.3745/ktccs.2021.10.2.39

블록체인과 딥러닝을 이용한 악성코드 탐지에 관한 연구
A Study on Malicious Code Detection Using Blockchain and Deep Learning 원문보기

정보처리학회논문지. KIPS transactions on computer and communication systems 컴퓨터 및 통신 시스템, v.10 no.2, 2021년, pp.39 - 46

이덕규 (서원대학교 정보보안학과)

초록
AI-Helper

최근 맬웨어에 의한 피해가 증가하고 있다. 기존의 시그니처 기반 안티 바이러스 솔루션은 제로 데이 공격 및 랜섬웨어와 같은 새로운 위협에 취약하다. 그럼에도 많은 기업은 문제점을 인식하고, 다중 엔드 포인트 보안 전략의 일부로 서명 기반 안티 바이러스 솔루션을 유지하고 있다. 본 논문에서는 차세대 안티 바이러스 솔루션으로 블록 체인과 딥 러닝 기술을 이용한 솔루션을 제안한다. 기존 DB 서버를 통해 업데이트되는 바이러스 백신 소프트웨어를 사용하여 탐지 유닛을 보완하고, 다양한 샘플과 형태를 사용하여 딥 러닝 용 DB 대신 블록 체인을 구성하여 신규 악성 코드 및 위조 악성 코드 탐지율을 높이는 방법을 제안한다.

Abstract ▼ AI-Helper

Damages by malware have recently been increasing. Conventional signature-based antivirus solutions are helplessly vulnerable to unprecedented new threats such as Zero-day attack and ransomware. Despite that, many enterprises have retained signature-based antivirus solutions as part of the multiple endpoints security strategy. They do recognize the problem. This paper proposes a solution using the blockchain and deep learning technologies as the next-generation antivirus solution. It uses the antivirus software that updates through an existing DB server to supplement the detection unit and organizes the blockchain instead of the DB for deep learning using various samples and forms to increase the detection rate of new malware and falsified malware.

주제어

표/그림 (14)

그림 Fig. 1. Accuracy Factor for Selected Approaches in Malware Detection[5]
그림 Fig. 2. The Data Analysis Methods in the Selected Articles[5]
그림 Fig. 3. Signature Generation Process[7]
그림 Fig. 4. Density Distribution of LOF and SOD[13]
그림 Fig. 5. Proposed Ensemble Technique[13]
그림 Fig. 6. CNN Algorithm Structure[14]
그림 Fig. 7. Blockchain Principle
그림 Fig. 8. Consortium Blockchain Principle
그림 Fig. 9. Flowchart of AV System
그림 Fig. 10. Extraction Flowchart
그림 Fig. 11. Image Convolve
그림 Fig. 12. Transaction Block
그림 Fig. 13. Flowchart of Blockchain Contract
표 Table 1 Comparison with Existing Systems

AI 본문요약
AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

문제 정의

Although its speed is weaker than other systems, it features superior security, diversity of malware detection, and real-time aspect with the blockchain than other systems. This paper proposes the blockchain technology to supplement such weaknesses of other systems.

제안 방법

These smart technologies help establish a sustainable environment by reducing bandwidth usage, latency, and power consumption in Internet of Things (IoT) based devices operating various smart city-based applications. The method proposed in this paper helps to build a more sustainable environment than the existing one by saving the manpower and time needed to define the existing anti-virus as a signature or act. Blockchain can be used to reduce the manpower and power required to collect data, while maintenance costs can also be significantly reduced compared to traditional methods, helping the environment in which the system is built and operated.
Users convert files into images with the module that extracts the grayscale of the file and register them in the blockchain, and the blockchain retrieves the registered images and classify them as malware or normal file. The method proposed in this paper uses the blockchain technology to add more data in real-time, enables more advanced machine learning through a wide range of datasets, and assures the diversity of the exhaustive search of the conventional deep learning method.
LOF will outperform SOD when run on low dimensional data and the opposite is true when considering high dimensional data. The proposed technique incorporates both of these values in order to create a more robust algorithm that leverages the advantages of the baseline algorithms. To find a more complex decision boundary, QDA is introduced to find a model that uses both values to classify the data.
Conventional signature-based antivirus solutions are helplessly vulnerable to unprecedented new threats such as Zero-day attack and ransomware. This paper proposes a solution using the blockchain and deep learning technologies as the next-generation antivirus solution. It supplements the conventional AV systems that compare and detects malware using the DB server and AV software by replacing the DB with the blockchain.

후속연구

Thus, the design of the system in this paper can be viewed positively with respect to the ongoing utilization of computing, and can also be expected to perform better.

참고문헌 (19)

Why even the best antivirus software isn't enough (and why you still need it) [Internet], https://www.csoonline.com/article/3316480/why-the-best-antivirus-software-isnt-enough.html
G. S. Kang, "Study on Cloud Computing-Based Malware Detection System," Master, Konkuk University, Korea, 2015.
S. Y. Choi, "Emulation-Based Abnormal Web Page Link Analysis to Detect Malware-istributing Networks," Master, Jeonnam National University, Korea, 2014.
Symantech - Internet Security Thresat Report [Internet], https://docs.broadcom.com/docs/istr-24-executive-summary-en
A. Souri and R. Hosseini, "A state-of-the-art survey of malware detection approaches using data mining techniques," Humand-centric Computing and Information Sciences, Vol.8, No.3, 2018.
A. Douglas, R. Holloway, J. Lohr, E. Morgan, and K. Harfoush, "Blockchains for constrained edge devices," Blockchain: Research and Applications, Vol.1, Iss.1-2, 2020.
S. W. Kim, "Real-Time Malware Detection in Intrusion Detection System," Master, Hanyang University, Korea, 2014.
J. W. Chang, "Study on Detecting Malware and Security Control Measures," Master, Korea University, 2014.
J. H. Park, "Effect of Private Blockchain Characteristics on Acceptance in Medical Sector," Master, Graduate School of Sungkyunkwan University, Korea, 2018.
G. Y. Lee, "Study of Applying Blockchain Technology and Record Management System," Master, Myongji University, Korea, 2019.
P. S. Goh, "Study on Use of Medical Information System with Blockchain," Master, Soongsil University, Korea, 2019.
D. G. Guh, "Study on Predicting Taxi Passenger Using Deep Learning," Master, University of Seoul, Korea, 2018.
D. T. Ramotsoela, G. P. Hancke, and A. M. Abu-Mahfouz, "Attack detection in water distribution systems using machine learning," Human-centric Computing and Information Sciences, Vol.9, No.13, 2019.
S. D. You, C. H. Liu, and W. K. Chen,"Comparative study of singing voice detection based on deep neural networks and ensemble learning," Human-centric Computing and Information Sciences, Vol.8, No.34, 2018.
S. N. Danilin and S. A. Shchanikov, "Neural network algorithms for determining the values of signal parameters in radio- electronic hardware," 2017 Dynamics of Systems, Mechanisms and Machines (Dynamics), Omsk, 2017, pp.1-4, 2017.
Y. B. Cho, "Detection Technique of Malware Using Deep Learning-Based R-CNN," Master, Daejeon University, Korea, 2018.
Y. Cheong, "Blockchain-Based Image Information Management System," Master, Ajou University, Korea, 2019.
S. I. Jung and H. W. Kim, "Web-Anti-MalWare Malware Detection System," Proceedings of the Korean Society of Computer Information Conference, pp.365-367, 2014.
D. Lee and J. H. Park, "Future Trends of AI-Based Smart Systems and Services: Challenges, Opportunities, and Solutions," Journal of Information Processing Systems, Vol.15, No.4, pp.717-723, 2019.

원문보기 상세보기

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증