Adversarial Deep Ensemble: Evasion Attacks and Defenses for Malware Detection

被引:84
|
作者
Li, Deqiang [1 ]
Li, Qianmu [1 ]
机构
[1] Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Peoples R China
关键词
Adversarial Machine Learning; Deep Neural Networks; Ensemble; Adversarial Malware Detection;
D O I
10.1109/TIFS.2020.3003571
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Malware remains a big threat to cyber security, calling for machine learning based malware detection. While promising, such detectors are known to be vulnerable to evasion attacks. Ensemble learning typically facilitates countermeasures, while attackers can leverage this technique to improve attack effectiveness as well. This motivates us to investigate which kind of robustness the ensemble defense or effectiveness the ensemble attack can achieve, particularly when they combat with each other. We thus propose a new attack approach, named mixture of attacks, by rendering attackers capable of multiple generative methods and multiple manipulation sets, to perturb a malware example without ruining its malicious functionality. This naturally leads to a new instantiation of adversarial training, which is further geared to enhancing the ensemble of deep neural networks. We evaluate defenses using Android malware detectors against 26 different attacks upon two practical datasets. Experimental results show that the new adversarial training significantly enhances the robustness of deep neural networks against a wide range of attacks, ensemble methods promote the robustness when base classifiers are robust enough, and yet ensemble attacks can evade the enhanced malware detectors effectively, even notably downgrading the VirusTotal service.
引用
收藏
页码:3886 / 3900
页数:15
相关论文
共 50 条
  • [41] On Effectiveness of Adversarial Examples and Defenses for Malware Classification
    Podschwadt, Robert
    Takabi, Hassan
    SECURITY AND PRIVACY IN COMMUNICATION NETWORKS, SECURECOMM, PT II, 2019, 305 : 380 - 393
  • [42] Black-Box Adversarial Attacks Against Deep Learning Based Malware Binaries Detection with GAN
    Yuan, Junkun
    Zhou, Shaofang
    Lin, Lanfen
    Wang, Feng
    Cui, Jia
    ECAI 2020: 24TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, 325 : 2536 - 2542
  • [43] Unveiling vulnerabilities in deep learning-based malware detection: Differential privacy driven adversarial attacks
    Taheri, Rahim
    Shojafar, Mohammad
    Arabikhan, Farzad
    Gegov, Alexander
    COMPUTERS & SECURITY, 2024, 146
  • [44] Adversarial Binaries: AI-guided Instrumentation Methods for Malware Detection Evasion
    Koch, Luke
    Begoli, Edmon
    ACM COMPUTING SURVEYS, 2025, 57 (05)
  • [45] DeepRobust: a Platform for Adversarial Attacks and Defenses
    Li, Yaxin
    Jin, Wei
    Xu, Han
    Tang, Jiliang
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 16078 - 16080
  • [46] On Adaptive Attacks to Adversarial Example Defenses
    Tramer, Florian
    Carlini, Nicholas
    Brendel, Wieland
    Madry, Aleksander
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [47] SoK: Realistic adversarial attacks and defenses for intelligent network intrusion detection
    Vitorino, Joao
    Praca, Isabel
    Maia, Eva
    COMPUTERS & SECURITY, 2023, 134
  • [48] A survey on adversarial attacks and defenses for object detection and their applications in autonomous vehicles
    Amirkhani, Abdollah
    Karimi, Mohammad Parsa
    Banitalebi-Dehkordi, Amin
    VISUAL COMPUTER, 2023, 39 (11): : 5293 - 5307
  • [49] A survey on adversarial attacks and defenses for object detection and their applications in autonomous vehicles
    Abdollah Amirkhani
    Mohammad Parsa Karimi
    Amin Banitalebi-Dehkordi
    The Visual Computer, 2023, 39 : 5293 - 5307
  • [50] Adversarial-Example Attacks Toward Android Malware Detection System
    Li, Heng
    Zhou, ShiYao
    Yuan, Wei
    Li, Jiahuan
    Leung, Henry
    IEEE SYSTEMS JOURNAL, 2020, 14 (01): : 653 - 656