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
  • [41] ADVERSARIAL EXAMPLE GENERATION METHOD FOR OBJECT DETECTION IN REMOTE SENSING IMAGES
    Jiang, Wanghan
    Zhou, Yue
    Jiang, Xue
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 5810 - 5813
  • [42] AYOLO: Development of a Real-Time Object Detection Model for the Detection of Secretly Cultivated Plants
    Yilmaz, Ali
    Yurtay, Yuksel
    Yurtay, Nilufer
    APPLIED SCIENCES-BASEL, 2025, 15 (05):
  • [43] Attention Distillation for Detection Transformers: Application to Real-Time Video Object Detection in Ultrasound
    Rubin, Jonathan
    Erkamp, Ramon
    Naidu, Ragha Srinivasa
    Thodiyil, Anumod Odungatta
    Chen, Alvin
    MACHINE LEARNING FOR HEALTH, VOL 158, 2021, 158 : 26 - 37
  • [44] Adversarial Training on Point Clouds for Sim-to-Real 3D Object Detection
    DeBortoli, Robert
    Li Fuxin
    Kapoor, Ashish
    Hollinger, Geoffrey A.
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (04): : 6662 - 6669
  • [45] Attentional and adversarial feature mimic for efficient object detection
    Hongxing Wang
    Yuquan Chen
    Mei Wu
    Xin Zhang
    Zheng Huang
    Weiping Mao
    The Visual Computer, 2023, 39 : 639 - 650
  • [46] An Enhanced Transferable Adversarial Attack Against Object Detection
    Shi, Guoqiang
    Lin, Zhi
    Peng, Anjie
    Zeng, Hui
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [47] Improving the Adversarial Robustness of Object Detection with Contrastive Learning
    Zeng, Weiwei
    Gao, Song
    Zhou, Wei
    Dong, Yunyun
    Wang, Ruxin
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT IX, 2024, 14433 : 29 - 40
  • [48] Attentional and adversarial feature mimic for efficient object detection
    Wang, Hongxing
    Chen, Yuquan
    Wu, Mei
    Zhang, Xin
    Huang, Zheng
    Mao, Weiping
    VISUAL COMPUTER, 2023, 39 (02): : 639 - 650
  • [49] A robust real time object detection and recognition algorithm for multiple objects
    Modwel G.
    Mehra A.
    Rakesh N.
    Mishra K.K.
    Recent Advances in Computer Science and Communications, 2021, 14 (01) : 331 - 338
  • [50] BED: A Real-Time Object Detection System for Edge Devices
    Wang, Guanchu
    Bhat, Zaid Pervaiz
    Jiang, Zhimeng
    Chen, Yi-Wei
    Zha, Daochen
    Reyes, Alfredo Costilla
    Niktash, Afshin
    Ulkar, Gorkem
    Okman, Erman
    Cai, Xuanting
    Hu, Xia
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022, 2022, : 4994 - 4998