On Embedding Backdoor in Malware Detectors Using Machine Learning

Shoichiro Sasaki, Seira Hidano, Toshihiro Uchibayashi, Takuo Suganuma, Masahiro Hiji, Shinsaku Kiyomoto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Researching for malware detection using machine learning is becoming active. However, conventional detection techniques do not consider the impact of attacks on machine learning, which has become complicated in recent years. In this research, we focus on data poisoning attack, which is one of the typical attacks on machine learning, and aim to clarify the influence of attacks on malware detection technology. Data poisoning attack is an attack method that intentionally manipulates the predicted result of a learned model by injecting poisoning data into training data, and by applying this, it is possible to embed a backdoor that induces mis-prediction of only specific input data. In this paper, we first propose an attack framework for backdoor embedding that prevents detection of only specific types of malware by data poisoning attack. Next, we will describe a method to generate poisoning data efficiently while avoiding attack detection by solving the optimization problem. Furthermore, we take malware detection technology using logistic regression and show the effectiveness of the our method through evaluation experiments using two datasets.

Original languageEnglish
Title of host publication2019 17th International Conference on Privacy, Security and Trust, PST 2019 - Proceedings
EditorsAli Ghorbani, Indrakshi Ray, Arash Habibi Lashkari, Jie Zhang, Rongxing Lu
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728132655
DOIs
Publication statusPublished - Aug 2019
Externally publishedYes
Event17th International Conference on Privacy, Security and Trust, PST 2019 - Fredericton, Canada
Duration: Aug 26 2019Aug 28 2019

Publication series

Name2019 17th International Conference on Privacy, Security and Trust, PST 2019 - Proceedings

Conference

Conference17th International Conference on Privacy, Security and Trust, PST 2019
CountryCanada
CityFredericton
Period8/26/198/28/19

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Safety, Risk, Reliability and Quality
  • Computer Networks and Communications
  • Information Systems and Management

Fingerprint Dive into the research topics of 'On Embedding Backdoor in Malware Detectors Using Machine Learning'. Together they form a unique fingerprint.

  • Cite this

    Sasaki, S., Hidano, S., Uchibayashi, T., Suganuma, T., Hiji, M., & Kiyomoto, S. (2019). On Embedding Backdoor in Malware Detectors Using Machine Learning. In A. Ghorbani, I. Ray, A. H. Lashkari, J. Zhang, & R. Lu (Eds.), 2019 17th International Conference on Privacy, Security and Trust, PST 2019 - Proceedings [8949034] (2019 17th International Conference on Privacy, Security and Trust, PST 2019 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PST47121.2019.8949034