基于重要特征的视觉目标跟踪可迁移黑盒攻击方法

姚睿; 朱享彬; 周勇; 王鹏; 张艳宁; 赵佳琦

doi:10.12263/DZXB.20220057

您当前的位置：

首页 >

文章列表页 >

基于重要特征的视觉目标跟踪可迁移黑盒攻击方法

学术论文 | 更新时间：2025-12-08

- 基于重要特征的视觉目标跟踪可迁移黑盒攻击方法
- Transferable Black Box Attack on Visual Object Tracking Based on Important Features
- 电子学报 2023年51卷第4期页码：826-834
- 作者机构：
  
  1.中国矿业大学计算机科学与技术学院,江苏徐州 221116
  2.矿山数字化教育部工程研究中心,江苏徐州 221116
  3.空天地海一体化大数据应用技术国家工程实验室,陕西西安 710129
  4.西北工业大学计算机学院,陕西西安 710129
- 作者简介：
  
  [ "姚睿男，1982年出生，河南南阳人.现为中国矿业大学计算机科学与技术学院教授、博士生导师.主要研究方向为计算机视觉、机器学习.E-mail: ruiyao@cumt.edu.cn" ]
  [ "朱享彬男，1997年出生，江西赣州人.现为中国矿业大学计算机科学与技术学院硕士研究生.主要研究方向为计算机视觉、机器学习. E-mail: TS20170131P31@cumt.edu.cn" ]
  [ "周勇男，1974年出生，江苏徐州人.现为中国矿业大学计算机科学与技术学院教授、博士生导师.主要研究方向为机器学习、数据挖掘.E-mail: yzhou@cumt.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(62172417);江苏省自然科学基金(BK20201346)
- DOI：10.12263/DZXB.20220057
  中图分类号： TP391.4;
- 收稿：2022-01-10，
  
  修回：2022-07-07，
  
  纸质出版：2023-04-25
- 稿件说明：
移动端阅览
姚睿,朱享彬,周勇等.基于重要特征的视觉目标跟踪可迁移黑盒攻击方法[J].电子学报,2023,51(04):826-834.

YAO Rui,ZHU Xiang-bin,ZHOU Yong,et al.Transferable Black Box Attack on Visual Object Tracking Based on Important Features[J].ACTA ELECTRONICA SINICA,2023,51(04):826-834.
姚睿,朱享彬,周勇等.基于重要特征的视觉目标跟踪可迁移黑盒攻击方法[J].电子学报,2023,51(04):826-834. DOI： 10.12263/DZXB.20220057.

YAO Rui,ZHU Xiang-bin,ZHOU Yong,et al.Transferable Black Box Attack on Visual Object Tracking Based on Important Features[J].ACTA ELECTRONICA SINICA,2023,51(04):826-834. DOI： 10.12263/DZXB.20220057.

摘要

视频目标跟踪的黑盒攻击方法受到越来越多的关注，目的是评估目标跟踪器的稳健性，进而提升跟踪器的安全性.目前大部分的研究都是基于查询的黑盒攻击，尽管取得较好的攻击效果，但在实际应用中往往不能获取大量的查询以进行攻击.本文提出一种基于迁移的黑盒攻击方法，通过对特征中与跟踪目标高度相关而不受源模型影响的重要特征进行攻击，将其重要程度降低，同时增强不重要的特征以实现具有可迁移性的攻击，即通过反向传播获得的所对应的梯度来体现其特征的重要程度，随后通过梯度得到的加权特征进行攻击.此外，本文使用视频相邻两帧之间相似这一时序信息，提出基于时序感知的特征相似性攻击方法，通过减小相邻帧之间的特征相似度以进行攻击.本文在目前主流的深度学习目标跟踪器上评估了提出的攻击方法，在多个数据集上的实验结果证明了本文方法的有效性及强可迁移性，在OTB数据集中，SiamRPN跟踪模型被攻击后跟踪成功率以及精确度分别下降了71.5%和79.9%.

Abstract

Black-box attack methods for video object tracking have received increasing attention in order to evaluate the robustness of object trackers and thus improve the security of trackers. Most of the current researches are based on query-based black-box attacks. Although fairly good attack effects are achieved

a large number of queries still cannot be obtained for attack in practical application. We propose a transfer based black-box attack method

which attacks the important features in the features that are highly related to the tracking target and are not affected by the source model

reduceing their importance and enhancing the unimportant features to realize the transferable attack. Specifically

the corresponding gradient is obtained by back propagation to reflect the importance of its features

and then the weighted feature obtained by the gradient is used to attack. In addition

this paper uses the temporal information of similarity between adjacent video frames to propose a sequential-aware feature similarity attack method to attack the object tracker by reducing the feature similarity between adjacent frames. This paper evaluates the proposed attack method on the current mainstream deep learning target tracker. The experimental results on multiple datasets prove the effectiveness and strong mobility of this method. In OTB benchmark

the tracking success rate and accuracy of SiamRPN tracking model are reduced by 71.5% and 79.9%

respectively.

关键词

Keywords

references

SZEGEDY C , ZAREMBA W , SUTSKEVER I , et al . Intriguing properties of neural networks [EB/OL ] . ( 2013-12-21 )[ 2022-01 ] . https://arxiv.org/abs/1312.6199 https://arxiv.org/abs/1312.6199 .

YAN B , WANG D , LU H C , et al . Cooling-shrinking attack: Blinding the tracker with imperceptible noises [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Seattle : IEEE , 2020 : 987 - 996 .

YAN X Y , CHEN X S , JIANG Y , et al . Hijacking tracker: A powerful adversarial attack on visual tracking [C ] // ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Barcelona : IEEE , 2020 : 2897 - 2901 .

LIANG S Y , WEI X X , YAO S Y , et al . Efficient adversarial attacks for visual object tracking [C ] // European Conference on Computer Vision - ECCV 2020 . Glasgow : Springer , 2020 : 34 - 50 .

CHEN X S , YAN X Y , ZHENG F , et al . One-shot adversarial attacks on visual tracking with dual attention [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Seattle : IEEE , 2020 : 10173 - 10182 .

GUO Q , CHENG Z Y , JUEFEI-XU F , et al . Learning to adversarially blur visual object tracking [C ] // 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Montreal : IEEE , 2022 : 10819 - 10828 .

GUO Q , XIE X F , JUEFEI-XU F , et al . SPARK: Spatial-aware online incremental attack against visual tracking [C ] // European Conference on Computer Vision - ECCV 2020 . Glasgow : Springer , 2020 : 202 - 219 .

JIA S , SONG Y B , MA C , et al . IoU attack: Towards temporally coherent black-box adversarial attack for visual object tracking [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Nashville : IEEE , 2021 : 6705 - 6714 .

WANG Z B , GUO H C , ZHANG Z F , et al . Feature importance-aware transferable adversarial attacks [C ] // 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Montreal : IEEE , 2022 : 7619 - 7628 .

WEI X , LIANG S , CHEN N , et al . Transferable adversarial attacks for image and video object detection [EB/OL ] . ( 2018-11-30 )[ 2022-01 ] . https://arxiv.org/abs/1811.12641 https://arxiv.org/abs/1811.12641 .

INKAWHICH N , LIANG K J , CARIN L , et al . Transferable perturbations of deep feature distributions [EB/OL ] . ( 2020-04-27 )[ 2022-01 ] . https://arxiv.org/abs/2004.12519 https://arxiv.org/abs/2004.12519 .

姚睿 , 朱享彬 , 周勇 , 等 . 一种基于重要特征的视觉目标跟踪可转移黑盒攻击方法 : CN114511593A [P ] . 2022-05-17 .

YAO R , ZHU X B , ZHOU Y , et al . Visual target tracking transferable black box attack method based on important features : CN114511593A [P ] . 2022-05-17 . (in Chinese)

LI B , WU W , WANG Q , et al . SiamRPN++: Evolution of Siamese visual tracking with very deep networks [C ] // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Long Beach : IEEE , 2020 : 4277 - 4286 .

YAO R , LIN G S , XIA S X , et al . Video object segmentation and tracking: A survey [J ] . ACM Transactions on Intelligent Systems and Technology , 2020 , 11 ( 4 ): 1 - 47 .

BERTINETTO L , VALMADRE J , HENRIQUES J F , et al . Fully-Convolutional Siamese Networks for Object Tracking [C ] // European Conference on Computer Vision . Amsterdam : Springer , 2016 : 850 - 865 .

丁新尧 , 张鑫 . 基于显著性特征的选择性目标跟踪算法 [J ] . 电子学报 , 2020 , 48 ( 1 ): 118 - 123 .

DING X Y , ZHANG X . Visual tracking with salient features and selective mechanism [J ] . Acta Electronica Sinica , 2020 , 48 ( 1 ): 118 - 123 . (in Chinese)

LI B , YAN J J , WU W , et al . High performance visual tracking with Siamese region proposal network [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City : IEEE , 2018 : 8971 - 8980 .

SONG Y B , MA C , WU X H , et al . VITAL: VIsual tracking via adversarial learning [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City : IEEE , 2018 : 8990 - 8999 .

陈丹 , 姚伯羽 . 运动模型引导的自适应核相关目标跟踪方法 [J ] . 电子学报 , 2021 , 49 ( 3 ): 550 - 558 .

CHEN D , YAO B Y . Adaptive response kernel correlation target tracking method guided by motion model [J ] . Acta Electronica Sinica , 2021 , 49 ( 3 ): 550 - 558 . (in Chinese)

DONG Y P , LIAO F Z , PANG T Y , et al . Boosting adversarial attacks with momentum [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City : IEEE , 2018 : 9185 - 9193 .

BHAT G , DANELLJAN M , VAN GOOL L , et al . Learning discriminative model prediction for tracking [C ] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Seoul : IEEE , 2020 : 6181 - 6190 .

DAI K N , ZHANG Y H , WANG D , et al . High-performance long-term tracking with meta-updater [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Seattle : IEEE , 2020 : 6297 - 6306 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

针对图像分类的鲁棒物理域对抗伪装

基于引导扩散模型的自然对抗补丁生成方法