Boosting Black-Box Adversarial Attacks with Meta Learning

被引:0
|
作者
Fu, Junjie [1 ,2 ]
Sun, Jian [1 ,2 ]
Wang, Gang [1 ,2 ]
机构
[1] Beijing Inst Technol, Key Lab Intelligent Control & Decis Complex Syst, Beijing 10081, Peoples R China
[2] Beijing Inst Technol, Chongqing Innovat Ctr, Chongqing 401120, Peoples R China
基金
中国国家自然科学基金; 国家重点研发计划;
关键词
Deep neural networks; adversarial examples; black-box attack; meta adversarial perturbation; transferability;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Deep neural networks (DNNs) have achieved remarkable success in diverse fields. However, it has been demonstrated that DNNs are very vulnerable to adversarial examples even in black-box settings. A large number of black-box attack methods have been proposed to in the literature. However, those methods usually suffer from low success rates and large query counts, which cannot fully satisfy practical purposes. In this paper, we propose a hybrid attack method which trains meta adversarial perturbations (MAPs) on surrogate models and performs black-box attacks by estimating gradients of the models. Our method uses the meta adversarial perturbation as an initialization and subsequently trains any black-box attack method for several epochs. Furthermore, the MAPs enjoy favorable transferability and universality, in the sense that they can be employed to boost performance of other black-box adversarial attack methods. Extensive experiments demonstrate that our method can not only improve the attack success rates, but also reduces the number of queries compared to other methods.
引用
收藏
页码:7308 / 7313
页数:6
相关论文
共 50 条
  • [1] Curls & Whey: Boosting Black-Box Adversarial Attacks
    Shi, Yucheng
    Wang, Siyu
    Han, Yahong
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 6512 - 6520
  • [2] Simple Black-box Adversarial Attacks
    Guo, Chuan
    Gardner, Jacob R.
    You, Yurong
    Wilson, Andrew Gordon
    Weinberger, Kilian Q.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [3] AutoAttacker: A reinforcement learning approach for black-box adversarial attacks
    Tsingenopoulos, Ilias
    Preuveneers, Davy
    Joosen, Wouter
    2019 4TH IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS (EUROS&PW), 2019, : 229 - 237
  • [4] Generalizable Black-Box Adversarial Attack With Meta Learning
    Yin, Fei
    Zhang, Yong
    Wu, Baoyuan
    Feng, Yan
    Zhang, Jingyi
    Fan, Yanbo
    Yang, Yujiu
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (03) : 1804 - 1818
  • [5] Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks
    Yatsura, Maksym
    Metzen, Jan Hendrik
    Hein, Matthias
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [6] Resiliency of SNN on Black-Box Adversarial Attacks
    Paudel, Bijay Raj
    Itani, Aashish
    Tragoudas, Spyros
    20TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2021), 2021, : 799 - 806
  • [7] Ensemble adversarial black-box attacks against deep learning systems
    Hang, Jie
    Han, Keji
    Chen, Hui
    Li, Yun
    PATTERN RECOGNITION, 2020, 101
  • [8] Substitute Meta-Learning for Black-Box Adversarial Attack
    Hu, Cong
    Xu, Hao-Qi
    Wu, Xiao-Jun
    IEEE SIGNAL PROCESSING LETTERS, 2022, 29 : 2472 - 2476
  • [9] Boosting Black-box Adversarial Attack with a Better Convergence
    Yin, Heng
    Wang, Jindong
    Mi, Yan
    Zhang, Xiaoning
    2020 5TH INTERNATIONAL CONFERENCE ON MECHANICAL, CONTROL AND COMPUTER ENGINEERING (ICMCCE 2020), 2020, : 1234 - 1238
  • [10] Black-box Adversarial Attacks in Autonomous Vehicle Technology
    Kumar, K. Naveen
    Vishnu, C.
    Mitra, Reshmi
    Mohan, C. Krishna
    2020 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR): TRUSTED COMPUTING, PRIVACY, AND SECURING MULTIMEDIA, 2020,