A Unified Multi-Scenario Attacking Network for Visual Object Tracking

Chen, Xuesong1; Fu, Canmiao2; Zheng, Feng4; Zhao, Yong3; Li, Hongsheng1; Luo, Ping5; Qi, Guo-Jun6

2021

35th AAAI Conference on Artificial Intelligence / 33rd Conference on Innovative Applications of Artificial Intelligence / 11th Symposium on Educational Advances in Artificial Intelligence

2159-5399

2374-3468

THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE

35

1097-1104

FEB 02-09, 2021

null,null,ELECTR NETWORK

2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE

Existing methods of adversarial attacks successfully generate adversarial examples to confuse Deep Neural Networks (DNNs) of image classification and object detection, resulting in wrong predictions. However, these methods are difficult to attack models of video object tracking, because the tracking algorithms could handle sequential information across video frames and the categories of targets tracked are normally unknown in advance. In this paper, we propose a Unified and Effective Network, named UEN, to attack visual object tracking models. There are several appealing characteristics of UEN: (1) UEN could produce various invisible adversarial perturbations according to different attack settings by using only one simple end-to-end network with three ingenious loss function; (2) UEN could generate general visible adversarial patch patterns to attack the advanced trackers in the real-world; (3) Extensive experiments show that UEN is able to attack many state-of-the-art trackers effectively (e.g. SiamRPN-based networks and DiMP) on popular tracking datasets including OTB100, UAV123, and GOT10K, making online real-time attacks possible. The attack results outperform the introduced baseline in terms of attacking ability and attacking efficiency.

通讯

英语

CPCI-S ; EI

National Natural Science Foundation of China[61972188]

Computer Science ; Education & Educational Research

Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Education, Scientific Disciplines

WOS:000680423501021

20222012114887

Aircraft detection ; Object detection

Ergonomics and Human Factors Engineering:461.4 ; Radar Systems and Equipment:716.2 ; Data Processing and Image Processing:723.2

Web of Science

1.Chinese Univ Hong Kong, Hong Kong, Peoples R China
2.Tencent, WeChat AI, Shenzhen, Guangdong, Peoples R China
3.Peking Univ, Beijing, Peoples R China
4.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen, Guangdong, Peoples R China
5.Univ Hong Kong, Hong Kong, Peoples R China
6.Futurewei Technol, Lab MAPLE, Santa Clara, CA USA

Chen, Xuesong,Fu, Canmiao,Zheng, Feng,et al. A Unified Multi-Scenario Attacking Network for Visual Object Tracking[C]. 2275 E BAYSHORE RD, STE 160, PALO ALTO, CA 94303 USA:ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE,2021:1097-1104.