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
  • [21] White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks
    Gil, Yotam
    Chai, Yoav
    Gorodissky, Or
    Berant, Jonathan
    2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, 2019, : 1373 - 1379
  • [22] Adversarial Black-Box Attacks on Vision-based Deep Reinforcement Learning Agents
    Tanev, Atanas
    Pavlitskaya, Svetlana
    Sigloch, Joan
    Roennau, Arne
    Dillmann, Ruediger
    Zoellner, J. Marius
    2021 IEEE INTERNATIONAL CONFERENCE ON INTELLIGENCE AND SAFETY FOR ROBOTICS (ISR), 2021, : 177 - 181
  • [23] Binary Black-Box Adversarial Attacks with Evolutionary Learning against IoT Malware Detection
    Wang, Fangwei
    Lu, Yuanyuan
    Wang, Changguang
    Li, Qingru
    WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2021, 2021
  • [24] Query-based Local Black-box Adversarial Attacks
    Shi, Jing
    Zhang, Xiaolin
    Xu, Enhui
    Wang, Yongping
    Zhang, Wenwen
    International Journal of Network Security, 2023, 25 (06) : 1048 - 1058
  • [25] Black-Box Adversarial Attacks against Audio Forensics Models
    Jiang, Yi
    Ye, Dengpan
    SECURITY AND COMMUNICATION NETWORKS, 2022, 2022
  • [26] Black-box adversarial attacks on XSS attack detection model
    Wang, Qiuhua
    Yang, Hui
    Wu, Guohua
    Choo, Kim-Kwang Raymond
    Zhang, Zheng
    Miao, Gongxun
    Ren, Yizhi
    COMPUTERS & SECURITY, 2022, 113
  • [27] Black-box transferable adversarial attacks based on ensemble advGAN
    Huang S.-N.
    Li Y.-X.
    Mao Y.-H.
    Ban A.-Y.
    Zhang Z.-Y.
    Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), 2022, 52 (10): : 2391 - 2398
  • [28] Simple Black-Box Adversarial Attacks on Deep Neural Networks
    Narodytska, Nina
    Kasiviswanathan, Shiva
    2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, : 1310 - 1318
  • [29] Heuristic Black-Box Adversarial Attacks on Video Recognition Models
    Wei, Zhipeng
    Chen, Jingjing
    Wei, Xingxing
    Jiang, Linxi
    Chua, Tat-Seng
    Zhou, Fengfeng
    Jiang, Yu-Gang
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 12338 - 12345
  • [30] Sensitive region-aware black-box adversarial attacks
    Lin, Chenhao
    Han, Sicong
    Zhu, Jiongli
    Li, Qian
    Shen, Chao
    Zhang, Youwei
    Guan, Xiaohong
    INFORMATION SCIENCES, 2023, 637