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
  • [41] Survey on adversarial attacks and defenses for object detection
    Wang, Xinxin
    Chen, Jing
    He, Kun
    Zhang, Zijun
    Du, Ruiying
    Li, Qiao
    She, Jisi
    Tongxin Xuebao/Journal on Communications, 2023, 44 (11): : 260 - 277
  • [42] Adversarial intensity awareness for robust object detection
    Cheng, Jikang
    Huang, Baojin
    Fang, Yan
    Han, Zhen
    Wang, Zhongyuan
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2025, 251
  • [43] ADA: Adversarial Data Augmentation for Object Detection
    Behpour, Sima
    Kitani, Kris M.
    Ziebart, Brian D.
    2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, : 1243 - 1252
  • [44] Adversarial Alignment for Source Free Object Detection
    Chu, Qiaosong
    Li, Shuyan
    Chen, Guangyi
    Li, Kai
    Li, Xiu
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 1, 2023, : 452 - 460
  • [45] Upcycling adversarial attacks for infrared object detection
    Kim, Hoseong
    Lee, Chanyong
    NEUROCOMPUTING, 2022, 482 : 1 - 13
  • [46] Understanding Object Detection Through an Adversarial Lens
    Chow, Ka-Ho
    Liu, Ling
    Gursoy, Mehmet Emre
    Truex, Stacey
    Wei, Wenqi
    Wu, Yanzhao
    COMPUTER SECURITY - ESORICS 2020, PT II, 2020, 12309 : 460 - 481
  • [47] Misleading attention and classification: An adversarial attack to fool object detection models in the real world
    Zhang, Haotian
    Ma, Xu
    COMPUTERS & SECURITY, 2022, 122
  • [48] A Real-Time Flame Detection Method Using Deformable Object Detection and Time Sequence Analysis
    Zhang, Jingyuan
    Shi, Bo
    Chen, Bin
    Chen, Heping
    Xu, Wangming
    SENSORS, 2023, 23 (20)
  • [49] Adversarial Examples for Semantic Segmentation and Object Detection
    Xie, Cihang
    Wang, Jianyu
    Zhang, Zhishuai
    Zhou, Yuyin
    Xie, Lingxi
    Yuille, Alan
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 1378 - 1387
  • [50] Real Time Video Processing and Object Detection on Android Smartphone
    Chaudhari, Sunil B.
    Patil, Shailaja A.
    2015 INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONICS, SIGNALS, COMMUNICATION AND OPTIMIZATION (EESCO), 2015,