Ensemble-based Blackbox Attacks on Dense Prediction

被引:7
|
作者
Cai, Zikui [1 ]
Tan, Yaoteng [1 ]
Asif, M. Salman [1 ]
机构
[1] Univ Calif Riverside, Riverside, CA 92521 USA
关键词
D O I
10.1109/CVPR52729.2023.00394
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose an approach for adversarial attacks on dense prediction models (such as object detectors and segmentation). It is well known that the attacks generated by a single surrogate model do not transfer to arbitrary (blackbox) victim models. Furthermore, targeted attacks are often more challenging than the untargeted attacks. In this paper, we show that a carefully designed ensemble can create effective attacks for a number of victim models. In particular, we show that normalization of the weights for individual models plays a critical role in the success of the attacks. We then demonstrate that by adjusting the weights of the ensemble according to the victim model can further improve the performance of the attacks. We performed a number of experiments for object detectors and segmentation to highlight the significance of the our proposed methods. Our proposed ensemble-based method outperforms existing blackbox attack methods for object detection and segmentation. Finally we show that our proposed method can also generate a single perturbation that can fool multiple blackbox detection and segmentation models simultaneously. Code is available at https://github.com/CSIPlab/EBAD.
引用
收藏
页码:4045 / 4055
页数:11
相关论文
共 50 条
  • [1] Improving Adversarial Attacks with Ensemble-Based Approaches
    Ji, Yapeng
    Zhou, Guoxu
    ARTIFICIAL INTELLIGENCE, CICAI 2022, PT II, 2022, 13605 : 15 - 29
  • [2] Blackbox Attacks via Surrogate Ensemble Search
    Cai, Zikui
    Song, Chengyu
    Krishnamurthy, Srikanth
    Roy-Chowdhury, Amit
    Asif, M. Salman
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [3] eDiaPredict: An Ensemble-based Framework for Diabetes Prediction
    Singh, Ashima
    Dhillon, Arwinder
    Kumar, Neeraj
    Hossain, M. Shamim
    Muhammad, Ghulam
    Kumar, Manoj
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2021, 17 (02)
  • [4] Ensemble-based prediction of RNA secondary structures
    Nima Aghaeepour
    Holger H Hoos
    BMC Bioinformatics, 14
  • [5] Hybrid Ensemble-Based Travel Mode Prediction
    Golik, Pawel
    Grzenda, Maciej
    Sienkiewicz, Elzbieta
    ADVANCES IN INTELLIGENT DATA ANALYSIS XXII, PT I, IDA 2024, 2024, 14641 : 191 - 202
  • [6] Ensemble-based prediction of RNA secondary structures
    Aghaeepour, Nima
    Hoos, Holger H.
    BMC BIOINFORMATICS, 2013, 14
  • [7] Towards ensemble-based use case point prediction
    Shukla, Suyash
    Kumar, Sandeep
    SOFTWARE QUALITY JOURNAL, 2023, 31 (03) : 843 - 864
  • [8] An ensemble-based stegware detection system for information hiding malware attacks
    Monika A.
    Eswari R.
    Journal of Ambient Intelligence and Humanized Computing, 2023, 14 (04) : 4401 - 4417
  • [9] Towards ensemble-based use case point prediction
    Suyash Shukla
    Sandeep Kumar
    Software Quality Journal, 2023, 31 : 843 - 864
  • [10] Ensemble-based classifiers
    Lior Rokach
    Artificial Intelligence Review, 2010, 33 : 1 - 39