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
  • [21] DbDHunter: An Ensemble-based Anomaly Detection Approach to Detect Drive-by Download Attacks
    Jodavi, Mehran
    Abadi, Mahdi
    Parhizkar, Elham
    2015 5TH INTERNATIONAL CONFERENCE ON COMPUTER AND KNOWLEDGE ENGINEERING (ICCKE), 2015, : 273 - 278
  • [22] Hybrid and ensemble-based soft computing techniques in bankruptcy prediction: a survey
    Antanas Verikas
    Zivile Kalsyte
    Marija Bacauskiene
    Adas Gelzinis
    Soft Computing, 2010, 14 : 995 - 1010
  • [23] Ensemble-Based Machine Learning Algorithm for Loan Default Risk Prediction
    Akinjole, Abisola
    Shobayo, Olamilekan
    Popoola, Jumoke
    Okoyeigbo, Obinna
    Ogunleye, Bayode
    MATHEMATICS, 2024, 12 (21)
  • [24] Model Ensemble-Based Prognostic Framework for Fatigue Crack Growth Prediction
    Hoang-Phuong Nguyen
    Zio, Enrico
    Liu, Jie
    2017 2ND INTERNATIONAL CONFERENCE ON SYSTEM RELIABILITY AND SAFETY (ICSRS), 2017, : 327 - 331
  • [25] Analyzing threat flow over network using ensemble-based dense network model
    Harita, U.
    Mohammed, Moulana
    SOFT COMPUTING, 2024, 28 (05) : 4171 - 4184
  • [26] Ensemble-based deep learning techniques for customer churn prediction model
    Subramanian, R. Siva
    Yamini, B.
    Sudha, Kothandapani
    Sivakumar, S.
    KYBERNETES, 2024,
  • [27] Beating the Uncertainties: Ensemble Forecasting and Ensemble-Based Data Assimilation in Modern Numerical Weather Prediction
    Zhang, Hailing
    Pu, Zhaoxia
    ADVANCES IN METEOROLOGY, 2010, 2010
  • [28] Analyzing threat flow over network using ensemble-based dense network model
    U. Harita
    Moulana Mohammed
    Soft Computing, 2024, 28 : 4171 - 4184
  • [29] Ensemble-based data assimilation
    Zhang, Fuqing
    Snyder, Chris
    BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY, 2007, 88 (04) : 565 - 568
  • [30] Ensemble-based sensitivity analysis
    Torn, Ryan D.
    Hakim, Gregory J.
    MONTHLY WEATHER REVIEW, 2008, 136 (02) : 663 - 677