Journal on Communications ›› 2021, Vol. 42 ›› Issue (11): 242-254.doi: 10.11959/j.issn.1000-436x.2021208

• Correspondences • Previous Articles    

Multi-level loss object tracking adversarial attack method based on spatial perception

Xu CHENG1,2,3, Yingying WANG1,2, Nianjie ZHANG1, Zhangjie FU1,2, Beijing CHEN1,2, Guoying ZHAO3   

  1. 1 School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China
    2 Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing 210044, China
    3 Center for Machine Vision and Signal Analysis, University of Oulu, Oulu FI-90014, Finland
  • Revised:2021-09-26 Online:2021-11-01 Published:2021-11-01
  • Supported by:
    The National Natural Science Foundation of China(61802058);The National Natural Science Foundation of China(61911530397);China Scholarship Council (CSC)(201908320175);China Postdoctoral Science Foundation(2019M651650);The Natural Science Foundation of Jiangsu Province(BK20201267);The Natural Science Foundation of Jiangsu Province(BK20200039)

Abstract:

In order to solve the problem that it is difficult for the existing adversarial disturbance techniques to effectively reduce the discrimination ability of the trackers and make the trajectory deviation rapidly, an effective object tracking adversarial attack method was proposed.First, deception loss, drift loss and attention mechanism-based loss was designed to jointly train generator based on the consideration of the high-level categories and the low-level features.Then, the clean image was sent to the trained generator to generate the adversarial samples that were used to interfere with the object trackers, which made the object trajectory deviation and reduced the tracking accuracy.Experimental results show that the proposed method achieves 54% reduction in success rate and 70% reduction in accuracy on OTB dataset, which can attack the object of tracking quickly in complex scenes.

Key words: video surveillance, network security, adversarial attack, deep learning, object tracking

CLC Number: 

No Suggested Reading articles found!