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
  • [31] Adaptive Temporal Grouping for Black-box Adversarial Attacks on Videos
    Wei, Zhipeng
    Chen, Jingjing
    Zhang, Hao
    Jiang, Linxi
    Jiang, Yu-Gang
    PROCEEDINGS OF THE 2022 INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, ICMR 2022, 2022, : 587 - 593
  • [32] An Optimized Black-Box Adversarial Simulator Attack Based on Meta-Learning
    Chen, Zhiyu
    Ding, Jianyu
    Wu, Fei
    Zhang, Chi
    Sun, Yiming
    Sun, Jing
    Liu, Shangdong
    Ji, Yimu
    ENTROPY, 2022, 24 (10)
  • [33] Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution
    Feng, Yan
    Wu, Baoyuan
    Fan, Yanbo
    Liu, Li
    Li, Zhifeng
    Xia, Shu-Tao
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 15074 - 15083
  • [34] Black-box Certification and Learning under Adversarial Perturbations
    Ashtiani, Hassan
    Pathak, Vinayak
    Urner, Ruth
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [35] 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
  • [36] Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks
    Yuan, Shengming
    Zhang, Qilong
    Gao, Lianli
    Cheng, Yaya
    Song, Jingkuan
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [37] Semantics aware adversarial malware examples generation for black-box attacks
    Peng, Xiaowei
    Xian, Hequn
    Lu, Qian
    Lu, Xiuqing
    APPLIED SOFT COMPUTING, 2021, 109
  • [38] Black-box attacks on dynamic graphs via adversarial topology perturbations
    Tao, Haicheng
    Cao, Jie
    Chen, Lei
    Sun, Hongliang
    Shi, Yong
    Zhu, Xingquan
    NEURAL NETWORKS, 2024, 171 : 308 - 319
  • [39] Adversarial Black-Box Attacks with Timing Side-Channel Leakage
    Nakai, Tsunato
    Suzuki, Daisuke
    Omatsu, Fumio
    Fujino, Takeshi
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2021, E104A (01) : 143 - 151
  • [40] Black-box Attacks on Spoofing Countermeasures Using Transferability of Adversarial Examples
    Zhang, Yuekai
    Jiang, Ziyan
    Villalba, Jesus
    Dehak, Najim
    INTERSPEECH 2020, 2020, : 4238 - 4242