축소된 특성집합을 이용한 CNN 기반의 안드로이드 악성코드 탐지
CNN-based Android Malware Detection Using Reduced Feature Set
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
딥러닝 기반 악성코드 탐지 및 분류모델의 성능은 특성집합을 어떻게 구성하느냐에 따라 크게좌우된다. 본 논문에서는 CNN 기반의 안드로이드 악성코드 탐지 시 탐지성능을 극대화할 수 있는 최적의 특성집합(feature set)을 선정하는 방법을 제안한다. 특성집합에 포함될 특성은 기계학습및 딥러닝에서 특성추출을 위해 널리 사용되는 Chi-Square test 알고리즘을 사용하여 선정하였다. CICANDMAL2017 데이터세트를 대상으로 선정된 36개의 특성을 이용하여 CNN 모델을 학습시킨후 악성코드 탐지성능을 측정한 결과 이진분류에서는 99.99%, 다중분류에서는 98.55%의 Accuracy 를 달성하였다.
Abstract
The performance of deep learning-based malware detection and classification models depends largely on how to construct a feature set to be applied to training. In this paper, we propose an approach to select the optimal feature set to maximize detection performance for CNN-based Android malware detection. The features to be included in the feature set were selected through the Chi-Square test algorithm, which is widely used for feature selection in machine learning and deep learning. To validate the proposed approach, the CNN model was trained using 36 characteristics selected for the CICANDMAL2017 dataset and then the malware detection performance was measured. As a result, 99.99% of Accuracy was achieved in binary classification and 98.55% in multiclass classification.
참고문헌 (16)
- MOBILE SECURITY REPORT 2021, "Check Point", U.S. Headquarters959 Skyway Road, ~ (2021)
- "Securelist. by Kaspersky, “IT threat evolution Q1 2021. Mobile statistics”"[URL]
- Byeon, J. Y, "RFA : Recursive Feature Addition Algorithm for Machine LearningBased Malware Classification", 26(2), pp.61~68 (2021)[DOI]
- Jundong Li, "Feature Selection", ACM Computing Surveys, 50(6), pp.1~45 (2018), Association for Computing Machinery (ACM)[DOI]
- Girish Chandrashekar, "A survey on feature selection methods", Computers & Electrical Engineering, 40(1), pp.16~28 (2014), Elsevier BV[DOI]
- Thaseen, I. S., "Integrated intrusion detection model using chi-square feature selection and ensemble of classifiers", Arabian Journal for Science and Engineering, 44(4), pp.3357~3368 (2018)
- Kumar, B. J., "Logistic regression for polymorphic malware detection using ANOVA F-test", 2017 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS), pp.1~5 (2017), IEEE
- N. Hoque, "MIFS-ND: A mutual information-based feature selection method", Expert Systems with Applications, 41(14), pp.6371~6385 (2014), Elsevier BV[DOI]
- Arora, A., "Minimizing network traffic features for android mobile malware detection", Proceedings of the 18th International Conference on Distributed Computing and Networking, pp.1~10 (2017)
- Lashkari, A. H., "Toward Developing a Systematic Approach to Generate Benchmark Android malware Datasets and Classification", Proc. of the 2018 International Carnahan Conference on Security Technology, pp.1~7 (2018)
- Chen, R., "Android malware identification based on traffic analysis", International Conference on Artificial Intelligence and Security, pp.293~303 (2019), Springer
- Bibi, I., "An effective Android ransomware detection through multi-factor Feature filtration and recurrent neural network", 2019 UK, 2019, 1~4[DOI]
- Abuthawabeh, M., "Enhanced android malware detection and family classification, using conversation-level network traffic Features", The International Arab Journal of Information Technology, 17(4A), pp.607~614 (2020)[DOI]
- Guyon, I., "An introduction to variable and feature selection", Journal of machine learning research, 3(3), pp.1157~1182 (2003)
- Rizgar Zebari, "A Comprehensive Review of Dimensionality Reduction Techniques for Feature Selection and Feature Extraction", Journal of Applied Science and Technology Trends, 1(2), pp.56~70 (2020), Interdisciplinary Publishing Academia[DOI]
- 강진원, "네트워크 트래픽 이미지화를 통한 안드로이드 악성코드 탐지", 정보과학회논문지, 47(8), pp.761~768 (2020), 한국정보과학회[DOI]