融合特征选择的Android恶意逃避攻击研究

陈镭; 杨章静; 黄璞

Chinese

您当前的位置：

首页 >

文章列表页 >

融合特征选择的Android恶意逃避攻击研究

更新时间：2026-09-04

- 融合特征选择的Android恶意逃避攻击研究
- Research on android malicious evasion attack based on feature selection
- 微电子学与计算机 2021年38卷第3期页码：89-94
- 作者机构：
  
  1. 南京审计大学机构信息工程学院,江苏,南京,211815
  2. 计算机软件新技术国家重点实验室机构 (南京大学),江苏,南京,210023
- 作者简介：
- 基金信息：
  
  国家自然科学基金 U1831127物联网产业化与智能生产协同创新中心(闽江学院)基金 IIC1705南京审计大学高教研究课题 2020JG049江苏省高校“青蓝工程”优秀青年骨干教师培养对象
- DOI：
  中图分类号：
- 纸质出版：2021
- 稿件说明：
移动端阅览
陈镭, 杨章静, 黄璞. 融合特征选择的Android恶意逃避攻击研究[J]. 微电子学与计算机, 2021, 38(3): 89-94.

CHEN Lei, YANG Zhang-jing, HUANG Pu. Research on android malicious evasion attack based on feature selection[J]. 2021, 38(3): 89-94.
陈镭, 杨章静, 黄璞. 融合特征选择的Android恶意逃避攻击研究[J]. 微电子学与计算机, 2021, 38(3): 89-94. DOI：

CHEN Lei, YANG Zhang-jing, HUANG Pu. Research on android malicious evasion attack based on feature selection[J]. 2021, 38(3): 89-94. DOI：

摘要

机器学习系统以其强大的自适应性、自学习能力，越来越多的应用到Android恶意软件检测领域，取得了显著的检测效果.然而，机器学习算法和样本本身还面临着诸多安全威胁，一些经过精心策划的攻击，希望颠覆这些算法并允许恶意行为对抗检测.首先以Drebin系统为例介绍了基于机器学习的Android恶意软件检测方法的原理，然后在攻击目标、攻击策略的基础了提出了针对机器学习分类器的逃避攻击模型.在综合考虑特征权重、可修改性、修改成本的基础上，提出了一种恶意对抗样本生成方法.实验结果表明，只需要修改很少量的特征，就能够逃避线性SVM分类器的检测，最后用一个具体的恶意样本逃避实例验证了提出方法的有效性.

Abstract

With its strong self-adaptability and self-learning ability

machine learning systems are increasingly used in the field of Android malware detection and have achieved remarkable detection results. However

machine learning algorithms and samples themselves also face many security threats

some well-designed attacks

hoping to subvert these algorithms and allow malicious behavior to resist detection. Firstly

the principle of machine learning-based detection method is introduced by taking the Drebin system as an example

and then an evasion attack model for machine learning classifier is proposed based on the attack target and attack strategy. Based on the comprehensive consideration of feature weight

modifiability and modification cost

proposes a malicious countermeasure sample generation method. The experimental results show that only a few features need to be modified to evade the detection of the linear SVM classifier. Finally

a specific example of malicious sample evasion attack verifies the effectiveness of the proposed method.

关键词

Keywords

references

SRNDIC N, LASKOV P. Practical evasion of a learning-based classifier: a case study[C]//2014 IEEE Symposium on Security and Privacy. San Jose, CA, USA: IEEE, 2014: 197-211. DOI: 10.1109/SP.2014.20.

张蕾, 崔勇, 刘静, 等. 机器学习在网络空间安全研究中的应用[J]. 计算机学报, 2018, 41(9): 1943-1975. DOI: 10.11897/SP.J.1016.2018.0 1943. ZHANG L, CUI Y, LIU J, et al. Application of machine learning in cyberspace security research[J]. Chinese Journal of Computers, 2018, 41(9): 1943-1975. DOI: 10.11897/SP.J.1016.2018.0 1943.

唐川, 张义, 杨岳湘, 等. DroidGAN: 基于DCGAN的Android对抗样本生成框架[J]. 通信学报, 2018, 39(Z1): 64-69. DOI: 10.11959/j.issn.1000-436x.2018178. TANG C, ZHANG Y, YANG Y X, et al. DroidGAN: android adversarial sample generation framework based on DCGAN[J]. Journal on Communications, 2018, 39(Z1): 64-69. DOI: 10.11959/j.issn.1000-436x.2018178.

张思思, 左信, 刘建伟. 深度学习中的对抗样本问题[J]. 计算机学报, 2019, 42(8): 1886-1904. DOI: 10.11897/SP.J.1016.2019.0 1886. ZHANG S S, ZUO X, LIU J W. The problem of the adversarial examples in deep learning[J]. Chinese Journal of Computers, 2019, 42(8): 1886-1904. DOI: 10.11897/SP.J.1016.2019.0 1886.

ABAID Z, KAAFAR M A, JHA S. Quantifying the impact of adversarial evasion attacks on machine learning based android malware classifiers[C]//2017 IEEE 16th International Symposium on Network Computing and Applications (NCA). Cambridge, MA, USA: IEEE, 2017: 1-10. DOI: 10.1109/NCA.2017.8171381.

CHEN L W, YE Y F, BOURLAI T. Adversarial machine learning in malware detection: arms race between evasion attack and defense[C]//2017 European Intelligence and Security Informatics Conference (EISIC). Athens, Greece: IEEE, 2017: 99-106. DOI: 10.1109/EISIC.2017.21.

SUCIU O, MaRGINEAN R, KAYA Y, et al. When does machine learning FAIL? Generalized transferability for evasion and poisoning attacks[C]//Proceedings of the 27th USENIX Conference on Security Symposium. Berkeley: USENIX Association, 2018: 1299-1316.

李盼, 赵文涛, 刘强, 等. 机器学习安全性问题及其防御技术研究综述[J]. 计算机科学与探索, 2018, 12(2): 171-184. DOI: 10.3778/j.issn.1673-9418.1708038. LI P, ZHAO W T, LIU Q, et al. Security issues and their countermeasuring techniques of machine learning: a survey[J]. Journal of Frontiers of Computer Science and Technology, 2018, 12(2): 171-184. DOI: 10.3778/j.issn.1673-9418.1708038.

ARP D, SPREITZENBARTH M, HUBNER M, et al. DREBIN: effective and explainable detection of android malware in your pocket[C]//NDSS Symposium. 2014. DOI: 10.14722/ndss.2014.23247.

HOU S F, YE Y F, SONG Y Q, et al. HinDroid: an intelligent android malware detection system based on structured heterogeneous information network[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Halifax, Nova Scotia, Canada: Association for Computing Machinery, 2017: 1507-1515. DOI: 10.1145/3097983.3098026.

CHEN L W, HOU S F, YE Y F, et al. SecureDroid: enhancing security of machine learning-based detection against adversarial android malware attacks[C]//Proceedings of the 33rd Annual Computer Security Applications Conference. Orlando, FL, USA: Association for Computing Machinery, 2017: 362-372. DOI: 10.1145/3134600.3134636.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于计算机视觉的电子元器件表面缺陷检测综述

混沌和柯西变异的蝗虫优化算法及特征选择

面向不平衡数据分类的高维超球体过采样方法

一种多X值输入下测试覆盖率损失的预测方法

基于量子计算的分类和聚类算法综述