Journals / Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi / 2019 / Cilt: 12 - Sayı: 2

Malware Detection by Using Markov Models of Hybrid Features

Melez Özelliklerin Modellenmesi ile Zararlı Yazılım Tespiti

Pages
50–63
Publication Date
2019-12-17
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

As a result of the tests we performed, the accuracy of the detection method was 96.8%.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Malware poses a great danger to computers and systems due to their capabilities.
📊
Key Findings & Data:In order to develop an automated detection system, malware must be well analyzed, and inclination of their evolution should be accurately understood.
💡
Conclusion & Impact:As a result of the tests we performed, the accuracy of the detection method was 96.8%.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Markov Zinciri · Derin Öğrenme · Dinamik Analiz

Abstract

Malware poses a great danger to computers and systems due to their capabilities. They are also affected by the development of effective detection systems and become more dangerous and equipped. In order to develop an automated detection system, malware must be well analyzed, and inclination of their evolution should be accurately understood. The runtime effects of malicious software on the computer and code structure should be examined in detail and precautions should be taken. The detection system proposed in this study makes a statistical meaning with Markov chain method using both behavior and code structure knowledge of malware. Then the model based on deep learning techniques is trained with the hybrid data source and detection environment is prepared. As a result of the tests we performed, the accuracy of the detection method was 96.8%.

Özet

Zararlı yazılımlar sahip oldukları yeteneklerden ötürü bilgisayar ve sistemlere büyük tehlike oluşturmaktadır. Etkin tespit sistemlerinin gelişmesinden aynı şekilde etkilenerek daha tehlikeli ve donanımlı hale gelmektedirler. Otomatik bir tespit sistemi geliştirmek için, zararlı yazılımlar iyi analiz edilmeli ve gelişim meyilleri doğru tespit edilmelidir. Zararlı yazılımların çalıştığı bilgisayarda yarattığı etkiler ve kod yapısı ayrıntılı incelenmeli ve öyle önlem alınmalıdır. Bu çalışmada önerilen tespit sistemi, zararlı yazılımın hem davranış hem kod yapısı bilgisini kullanarak Markov zinciri yöntemi ile istatistiksel bir anlam çıkarmaktadır. Daha sonra derin öğrenme teknikleri ile temellendirilmiş model melez veri kaynağı ile eğitilmiş ve tespit ortamı hazırlanmıştır. Yaptığımız testler sonucunda önerilen tespit yöntemi %96,8’lik doğruluk göstermiştir.

🔖

Cite This Article

NAR, M., SOĞUKPINAR, İ. (2019). Malware Detection by Using Markov Models of Hybrid Features. Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, Cilt: 12 - Sayı: 2, 50–63. https://ajindex.com/articles/812051

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (12)

  1. MalwareBytes-Labs. 2019 State of Malware, 2019. https://blog.malwarebytes.com/malwarebytes-news/ctnt-report (accessed April 15, 2019)
  2. AV-Test-Institute. 2019 New Malware, 2019. https://https://www.av-test.org/en/statistics/malware/(accessed April 15, 2019)
  3. Rajeswaran, D., Di Troia, F., Austin, T. H., & Stamp, M. (2018). Function call graphs versus machine learning for malware detection. In Guide to Vulnerability Analysis for Computer Networks and Systems (pp. 259-279). Springer, Cham
  4. Pektaş, A., & Acarman, T. (2017). Malware classification based on API calls and behaviour analysis. IET Information Security, 12(2), 107-117
  5. Vemparala, S., Di Troia, F., Corrado, V. A., Austin, T. H., & Stamo, M. (2016, March). Malware detection using dynamic birthmarks. In Proceedings of the 2016 ACM on International Workshop on Security And Privacy Analytics (pp. 41-46). ACM
  6. Safa, H., Nassar, M., & Al Orabi, W. A. R. (2019, June). Benchmarking Convolutional and Recurrent Neural Networks for Malware Classification. In 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC) (pp. 561-566). IEEE
  7. Afianian, A., Niksefat, S., Sadeghiyan, B., & Baptiste, D. (2018). Malware Dynamic Analysis Evasion Techniques: A Survey. arXiv preprint arXiv:1811.01190
  8. Sartea, R., & Farinelli, A. (2018, July). Detection of Intelligent Agent Behaviors Using Markov Chains. In Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems (pp. 2064-2066). International Foundation for Autonomous Agents and Multiagent Systems
  9. Martín, A., Rodríguez-Fernández, V., & Camacho, D. (2018). CANDYMAN: Classifying Android malware families by modelling dynamic traces with Markov chains. Engineering Applications of Artificial Intelligence, 74, 121-133
  10. Anderson, B., Storlie, C., & Lane, T. (2012, October). Improving malware classification: bridging the static/dynamic gap. In Proceedings of the 5th ACM workshop on Security and artificial intelligence (pp. 3-14). ACM
  11. Kolosnjaji, B., Demontis, A., Biggio, B., Maiorca, D., Giacinto, G., Eckert, C., & Roli, F. (2018, September). Adversarial malware binaries: Evading deep learning for malware detection in executables. In 2018 26th European Signal Processing Conference (EUSIPCO) (pp. 533-537). IEEE
  12. Demetrio, L., Biggio, B., Lagorio, G., Roli, F., & Armando, A. (2019). Explaining Vulnerabilities of Deep Learning to Adversarial Malware Binaries. arXiv prepr