Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models

被引:0
|
作者
Wang, Zeyuan [1 ]
Sha, Chaofeng [1 ]
Yang, Su [1 ]
机构
[1] Fudan Univ, Shanghai Key Lab Intelligent Informat Proc, Sch Comp Sci, Shanghai, Peoples R China
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We explore the black-box adversarial attack on video recognition models. Attacks are only performed on selected key regions and key frames to reduce the high computation cost of searching adversarial perturbations on a video due to its high dimensionality. To select key frames, one way is to use heuristic algorithms to evaluate the importance of each frame and choose the essential ones. However, it is time inefficient on sorting and searching. In order to speed up the attack process, we propose a reinforcement learning based frame selection strategy. Specifically, the agent explores the difference between the original class and the target class of videos to make selection decisions. It receives rewards from threat models which indicate the quality of the decisions. Besides, we also use saliency detection to select key regions and only estimate the sign of gradient instead of the gradient itself in zeroth order optimization to further boost the attack process. We can use the trained model directly in the untargeted attack or with little fine-tune in the targeted attack, which saves computation time. A range of empirical results on real datasets demonstrate the effectiveness and efficiency of the proposed method.
引用
收藏
页码:3162 / 3168
页数:7
相关论文
共 50 条
  • [1] Coreset Learning-Based Sparse Black-Box Adversarial Attack for Video Recognition
    Chen, Jiefu
    Chen, Tong
    Xu, Xing
    Zhang, Jingran
    Yang, Yang
    Shen, Heng Tao
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2024, 19 : 1547 - 1560
  • [2] Sparse Black-Box Video Attack with Reinforcement Learning
    Wei, Xingxing
    Yan, Huanqian
    Li, Bo
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 130 (06) : 1459 - 1473
  • [3] Sparse Black-Box Video Attack with Reinforcement Learning
    Xingxing Wei
    Huanqian Yan
    Bo Li
    [J]. International Journal of Computer Vision, 2022, 130 : 1459 - 1473
  • [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] 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
    [J]. 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
  • [6] SSQLi: A Black-Box Adversarial Attack Method for SQL Injection Based on Reinforcement Learning
    Guan, Yuting
    He, Junjiang
    Li, Tao
    Zhao, Hui
    Ma, Baoqiang
    [J]. FUTURE INTERNET, 2023, 15 (04):
  • [7] Adversarial Eigen Attack on Black-Box Models
    Zhou, Linjun
    Cui, Peng
    Zhang, Xingxuan
    Jiang, Yinan
    Yang, Shiqiang
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 15233 - 15241
  • [8] A Black-Box Adversarial Attack via Deep Reinforcement Learning on the Feature Space
    Li, Lyue
    Rezapour, Amir
    Tzeng, Wen-Guey
    [J]. 2021 IEEE CONFERENCE ON DEPENDABLE AND SECURE COMPUTING (DSC), 2021,
  • [9] Improved Adversarial Attack against Black-box Machine Learning Models
    Xu, Jiahui
    Wang, Chen
    Li, Tingting
    Xiang, Fengtao
    [J]. 2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 5907 - 5912
  • [10] Generalizable Black-Box Adversarial Attack With Meta Learning
    Yin, Fei
    Zhang, Yong
    Wu, Baoyuan
    Feng, Yan
    Zhang, Jingyi
    Fan, Yanbo
    Yang, Yujiu
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (03) : 1804 - 1818