Adversarial Detection: Attacking Object Detection in Real Time

被引:0
|
作者
Wu, Han [1 ]
Yunas, Syed [2 ]
Rowlands, Sareh [1 ]
Ruan, Wenjie [1 ]
Wahlström, Johan [1 ]
机构
[1] Univ Exeter, Comp Sci, Exeter, Devon, England
[2] Univ West England, Comp Sci, Bristol, Avon, England
来源
2023 IEEE INTELLIGENT VEHICLES SYMPOSIUM, IV | 2023年
关键词
Adversarial Attacks; Object Detection;
D O I
10.1109/IV55152.2023.10186608
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are vulnerable to adversarial attacks. However, prior research primarily focuses on attacking static images or offline videos. Therefore, it is still unclear if such attacks could jeopardize real-world robotic applications in dynamic environments. This paper bridges this gap by presenting the first real-time online attack against object detection models. We devise three attacks that fabricate bounding boxes for nonexistent objects at desired locations. The attacks achieve a success rate of about 90% within about 20 iterations. The demo video is available at https://youtu.be/zJZ1aNlXsMU.
引用
收藏
页数:7
相关论文
共 50 条
  • [31] Performance Evaluation of Real-Time Object Detection Algorithms
    Srisuk, Sanun
    Suwannapong, Chanwit
    Kitisriworapan, Songrit
    Kaewsong, Apiwut
    Ongkittikul, Surachai
    2019 7TH INTERNATIONAL ELECTRICAL ENGINEERING CONGRESS (IEECON 2019), 2019,
  • [32] Real-time multiple object tracking and anomaly detection
    Han, M
    Gong, YH
    STORAGE AND RETRIEVAL METHODS AND APPLICATIONS FOR MULTIMEDIA 2005, 2005, 5682 : 173 - 182
  • [33] Real Time Object Detection Based on FPGA with Big Data
    Zhang, Peiyue
    Xu, Zhan
    Liu, Pengcheng
    Zhao, Yiyang
    Wang, Lian
    Ma, Yuntao
    Wang, Jian
    2018 4TH INTERNATIONAL CONFERENCE ON BIG DATA COMPUTING AND COMMUNICATIONS (BIGCOM 2018), 2018, : 54 - 59
  • [34] Real Time Object Detection Based on Deep Neural Network
    Teama, Tarek
    Ma, Hongbin
    Maher, Ali
    Kassab, Mohamed A.
    INTELLIGENT ROBOTICS AND APPLICATIONS, ICIRA 2019, PT IV, 2019, 11743 : 493 - 504
  • [35] Real-Time Object Detection for Visually Challenged People
    Vaidya, Sunit
    Shah, Naisha
    Shah, Niti
    Shankarmani, Radha
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND CONTROL SYSTEMS (ICICCS 2020), 2020, : 311 - 316
  • [36] Towards Real-Time Object Detection on Embedded Systems
    Mao, Huizi
    Yao, Song
    Tang, Tianqi
    Li, Boxun
    Yao, Jun
    Wang, Yu
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING, 2018, 6 (03) : 417 - 431
  • [37] An Intelligent Real-Time Object Detection System on Drones
    Chen, Chao
    Min, Hongrui
    Peng, Yi
    Yang, Yongkui
    Wang, Zheng
    APPLIED SCIENCES-BASEL, 2022, 12 (20):
  • [38] Improve Real-time Object Detection with Feature Enhancement
    Wei, Wendian
    Hu, Yu
    PROCEEDINGS OF 2019 IEEE 8TH JOINT INTERNATIONAL INFORMATION TECHNOLOGY AND ARTIFICIAL INTELLIGENCE CONFERENCE (ITAIC 2019), 2019, : 235 - 238
  • [39] CPU Based YOLO: A Real Time Object Detection Algorithm
    Ullah, Md Bahar
    2020 IEEE REGION 10 SYMPOSIUM (TENSYMP) - TECHNOLOGY FOR IMPACTFUL SUSTAINABLE DEVELOPMENT, 2020, : 552 - 555
  • [40] Near Real-time Object Detection in RGBD Data
    Haensch, Ronny
    Kaiser, Stefan
    Helwich, Olaf
    PROCEEDINGS OF THE 12TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISIGRAPP 2017), VOL 5, 2017, : 179 - 186