Malicious code detection is one of the important missions of malicious code analysis. Current researches on the detection of malicious code mostly focused on single classifier, whereas the single classifier is not suitable for the detection based on features of different types. We utilized multi-classifiers ensemble based on fuzzy integral to improve the accuracy of the detection framework. A framework based on the Choquet fuzzy integral was proposed to fuse the analysis results of the base classifiers with different features. And the genetic algorithm was used to obtain the fuzzy measure. Finally, the result of Choquet fuzzy integral was compared to a threshold predefined to determine the maliciousness of binary code. Experiment showed that the framework proposed in this paper could be used to determine the maliciousness of binary code more accurately.
목차
Abstract 1. Introduction 2. Related Works 3. Basic of Fuzzy Integral 3.1. Fuzzy Measure 3.2. Fuzzy Integral 4. Detection Framework Based on Multi-classifiers Ensemble 4.1. Overview of the Detection Framework 4.2. Architecture of Static Analysis 4.3. Fuzzy Measure Calculation based on Genetic Algorithm 5. Experiments and Results 6. Conclusion and Future Work Acknowledgments References
보안공학연구지원센터(IJSIA) [Science & Engineering Research Support Center, Republic of Korea(IJSIA)]
설립연도
2006
분야
공학>컴퓨터학
소개
1. 보안공학에 대한 각종 조사 및 연구
2. 보안공학에 대한 응용기술 연구 및 발표
3. 보안공학에 관한 각종 학술 발표회 및 전시회 개최
4. 보안공학 기술의 상호 협조 및 정보교환
5. 보안공학에 관한 표준화 사업 및 규격의 제정
6. 보안공학에 관한 산학연 협동의 증진
7. 국제적 학술 교류 및 기술 협력
8. 보안공학에 관한 논문지 발간
9. 기타 본 회 목적 달성에 필요한 사업
간행물
간행물명
International Journal of Security and Its Applications
간기
격월간
pISSN
1738-9976
수록기간
2008~2016
등재여부
SCOPUS
십진분류
KDC 505DDC 605
이 권호 내 다른 논문 / International Journal of Security and Its Applications Vol.10 No.6