Adversarial Detection: Attacking Object Detection in Real Time
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 5 Sep 2022.
Builds on
21 of 29 references.
References · 21
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2018YOLOv3: An Incremental Improvementcited by 2,652
- 2016Adversarial examples in the physical worldcited by 1,762
- 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
- 2017Adversarial Patchcited by 514
- 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
- 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
9 more
- 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 146
- 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
- 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 123
- 2019On Physical Adversarial Patches for Object Detectioncited by 93
- 2019Wasserstein Adversarial Examples via Projected Sinkhorn Iterationscited by 89
- 2019Adversarial camera stickers: A physical camera-based attack on deep learning systemscited by 69
- 2015Distributional Smoothing with Virtual Adversarial Trainingcited by 61
- 2015Adversarial Manipulation of Deep Representationscited by 56
- 2020Dynamic Adversarial Patch for Evading Object Detection Modelscited by 20
Built on by
Citing papers per year: 2024: 2.
2 papers.