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
  • [41] Prediction and Analysis of PM 2.5 Concentration in Seoul Using Ensemble-based Model
    Ryu, Minji
    Son, Sanghun
    Kim, Jinsoo
    KOREAN JOURNAL OF REMOTE SENSING, 2022, 38 (06) : 1191 - 1205
  • [42] Computational Prediction of Cervical Cancer Diagnosis Using Ensemble-Based Classification Algorithm
    Gupta, Surbhi
    Gupta, Manoj K.
    COMPUTER JOURNAL, 2022, 65 (06): : 1527 - 1539
  • [43] Ensemble-Based Observation Targeting for Improving Ozone Prediction in Houston and the Surrounding Area
    Bei, Naifang
    Zhang, Fuqing
    Nielsen-Gammon, John W.
    PURE AND APPLIED GEOPHYSICS, 2012, 169 (03) : 539 - 554
  • [44] Ensemble-Based Observation Targeting for Improving Ozone Prediction in Houston and the Surrounding Area
    Naifang Bei
    Fuqing Zhang
    John W. Nielsen-Gammon
    Pure and Applied Geophysics, 2012, 169 : 539 - 554
  • [45] Prediction of drug synergy in cancer using ensemble-based machine learning techniques
    Singh, Harpreet
    Rana, Prashant Singh
    Singh, Urvinder
    MODERN PHYSICS LETTERS B, 2018, 32 (11):
  • [46] Noninvasive prediction of metastasis in esophageal cancer using ensemble-based feature selection
    Aalam, Syed Wajid
    Ahanger, Ab Basit
    Assad, Assif
    Macha, Muzafar A.
    Bhat, Muzafar Rasool
    INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT, 2024,
  • [47] Prediction of landslide displacement with an ensemble-based extreme learning machine and copula models
    Huajin Li
    Qiang Xu
    Yusen He
    Jiahao Deng
    Landslides, 2018, 15 : 2047 - 2059
  • [48] An ensemble-based model for prediction of academic performance of students in undergrad professional course
    Kamal, Preet
    Ahuja, Sachin
    JOURNAL OF ENGINEERING DESIGN AND TECHNOLOGY, 2019, 17 (04) : 769 - 781
  • [49] Efficient Visualization for an Ensemble-based System
    Toth, Janos
    Tornai, Robert
    Labancz, Imre
    Hajdu, Andras
    ACTA POLYTECHNICA HUNGARICA, 2019, 16 (02) : 59 - 75
  • [50] Ensemble-based Network Edge Processing
    Petri, Ioan
    Zamani, Ali Reza
    Balouek-Thomert, Daniel
    Rana, Omer
    Rezgui, Yacine
    Parashar, Manish
    2018 IEEE/ACM 11TH INTERNATIONAL CONFERENCE ON UTILITY AND CLOUD COMPUTING (UCC), 2018, : 133 - 142