Black-box Adversarial Attacks in Autonomous Vehicle Technology

被引:15
|
作者
Kumar, K. Naveen [1 ]
Vishnu, C. [1 ]
Mitra, Reshmi [2 ]
Mohan, C. Krishna [1 ]
机构
[1] Indian Inst Technol Hyderabad, Kandi, Telangana, India
[2] Southeast Missouri State Univ, Cape Girardeau, MO 63701 USA
关键词
adversarial attacks; black-box attacks; deep learning methods; autonomous vehicles;
D O I
10.1109/AIPR50011.2020.9425267
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Despite the high quality performance of the deep neural network in real-world applications, they are susceptible to minor perturbations of adversarial attacks. This is mostly undetectable to human vision. The impact of such attacks has become extremely detrimental in autonomous vehicles with real-time "safety" concerns. The black-box adversarial attacks cause drastic misclassification in critical scene elements such as road signs and traffic lights leading the autonomous vehicle to crash into other vehicles or pedestrians. In this paper, we propose a novel query-based attack method called Modified Simple black-box attack (M-SimBA) to overcome the use of a white-box source in transfer based attack method. Also, the issue of late convergence in a Simple black-box attack (SimBA) is addressed by minimizing the loss of the most confused class which is the incorrect class predicted by the model with the highest probability, instead of trying to maximize the loss of the correct class. We evaluate the performance of the proposed approach to the German Traffic Sign Recognition Benchmark (GTSRB) dataset. We show that the proposed model outperforms the existing models like Transfer-based projected gradient descent (T-PGD), SimBA in terms of convergence time, flattening the distribution of confused class probability, and producing adversarial samples with least confidence on the true class.
引用
收藏
页数:7
相关论文
共 50 条
  • [1] Simple Black-box Adversarial Attacks
    Guo, Chuan
    Gardner, Jacob R.
    You, Yurong
    Wilson, Andrew Gordon
    Weinberger, Kilian Q.
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [2] Resiliency of SNN on Black-Box Adversarial Attacks
    Paudel, Bijay Raj
    Itani, Aashish
    Tragoudas, Spyros
    [J]. 20TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2021), 2021, : 799 - 806
  • [3] Black-box adversarial attacks by manipulating image attributes
    Wei, Xingxing
    Guo, Ying
    Li, Bo
    [J]. INFORMATION SCIENCES, 2021, 550 : 285 - 296
  • [4] Black-box Adversarial Attacks on Video Recognition Models
    Jiang, Linxi
    Ma, Xingjun
    Chen, Shaoxiang
    Bailey, James
    Jiang, Yu-Gang
    [J]. PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, : 864 - 872
  • [5] Physical Black-Box Adversarial Attacks Through Transformations
    Jiang, Wenbo
    Li, Hongwei
    Xu, Guowen
    Zhang, Tianwei
    Lu, Rongxing
    [J]. IEEE TRANSACTIONS ON BIG DATA, 2023, 9 (03) : 964 - 974
  • [6] Boosting Black-Box Adversarial Attacks with Meta Learning
    Fu, Junjie
    Sun, Jian
    Wang, Gang
    [J]. 2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 7308 - 7313
  • [7] A review of black-box adversarial attacks on image classification
    Zhu, Yanfei
    Zhao, Yaochi
    Hu, Zhuhua
    Luo, Tan
    He, Like
    [J]. NEUROCOMPUTING, 2024, 610
  • [8] Curls & Whey: Boosting Black-Box Adversarial Attacks
    Shi, Yucheng
    Wang, Siyu
    Han, Yahong
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 6512 - 6520
  • [9] Boundary Defense Against Black-box Adversarial Attacks
    Aithal, Manjushree B.
    Li, Xiaohua
    [J]. 2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 2349 - 2356
  • [10] Black-box Adversarial Attacks with Limited Queries and Information
    Ilyas, Andrew
    Engstrom, Logan
    Athalye, Anish
    Lin, Jessy
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80