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
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] Moving object detection for real-time applications
    Maddalena, Lucia
    Petrosino, Alfredo
    14TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS, 2007, : 542 - +
  • [32] Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks
    Han, Husheng
    Hu, Xing
    Hao, Yifan
    Xu, Kaidi
    Dang, Pucheng
    Wang, Ying
    Zhao, Yongwei
    Du, Zidong
    Guo, Qi
    Wang, Yanzhi
    Zhang, Xishan
    Chen, Tianshi
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2024, 43 (01) : 366 - 379
  • [33] Using Popular Object Detection Methods for Real Time Forest Fire Detection
    Wu, Shixiao
    Zhang, Libing
    2018 11TH INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DESIGN (ISCID), VOL 1, 2018, : 280 - 284
  • [34] Real-time detection of track fasteners based on object detection and FPGA
    Xiao, Tian
    Xu, Tianhua
    Wang, Guang
    MICROPROCESSORS AND MICROSYSTEMS, 2023, 100
  • [35] High detection-rate cascades for real-time object detection
    Masnadi-Shirazi, Hamed
    Vasconcelos, Nuno
    2007 IEEE 11TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1-6, 2007, : 253 - 258
  • [36] Real-time Scene Change Detection with Object Detection for Automated Stock Verification
    Yedla, Sandeep Kumar
    Manikandan, V. M.
    Panchami, V
    2020 5TH INTERNATIONAL CONFERENCE ON DEVICES, CIRCUITS AND SYSTEMS (ICDCS' 20), 2020, : 157 - 161
  • [37] Real-Time Monitoring for Detection of Adversarial Subtle Process Variations
    Li, Yeni
    Sundaram, Arvind
    Abdel-Khalik, Hany S.
    Talbot, Paul W.
    NUCLEAR SCIENCE AND ENGINEERING, 2022, 196 (05) : 544 - 567
  • [38] A Methodology for Early Detection of Plant Diseases Using Real Time Object Detection Algorithm
    Walia, Ranjeet
    Sharma, Shivam
    Shrivastava, Swapnil
    SMART AND SUSTAINABLE AGRICULTURE, SSA 2021, 2021, 1470 : 122 - 139
  • [39] Lightweight adversarial network for salient object detection
    Huang, Lili
    Li, Guanbin
    Li, Ya
    Lin, Liang
    NEUROCOMPUTING, 2020, 381 (381) : 130 - 140
  • [40] Universal adversarial perturbations against object detection
    Li, Debang
    Zhang, Junge
    Huang, Kaiqi
    PATTERN RECOGNITION, 2021, 110