paper-with-me

Papers

Adversarial Detection: Attacking Object Detection in Real Time

2022-09-05 · Han Wu, Syed Yunas, Sareh Rowlands, Wenjie Ruan, Johan Wahlstrom

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.

📄 PDF Abstract BibTeX arXiv:2209.01962

Code (1)

wuhanstudio/adversarial-detection 공식 구현 tf

Tasks

Objectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

Adversarial Attention Perturbations for Large Object Detection Transformers

2025-08-05 · Zachary Yahn, Selim Furkan Tekin, Fatih Ilhan, Sihao Hu 외 arxiv

Adversarial perturbations are useful tools for exposing vulnerabilities in neural networks. Existing adversarial perturbation methods for object detection are either limited to attacking CNN-based detectors or weak again…

Object Detection

Attacking Important Pixels for Anchor-free Detectors

2023-01-26 · Yunxu Xie, Shu Hu, Xin Wang, Quanyu Liao 외

Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change the prediction result. Existing adversarial attacks on object detection focus on attacking an…

Adversarial Attackobject-detectionObject DetectionPose Estimation

Transferable Adversarial Examples for Anchor Free Object Detection

2021-06-03 · Quanyu Liao, Xin Wang, Bin Kong, Siwei Lyu 외

Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change prediction result. The vulnerability has led to a surge of research in this direction, includ…

Adversarial AttackObjectobject-detectionObject Detection

Category-wise Attack: Transferable Adversarial Examples for Anchor Free Object Detection

2020-02-10 · Quanyu Liao, Xin Wang, Bin Kong, Siwei Lyu 외

Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbations can completely change the classification results. Their vulnerability has led to a surge of research in this direc…

Objectobject-detectionObject Detection

Transferable Adversarial Attacks for Image and Video Object Detection

2018-11-30 · Xingxing Wei, Siyuan Liang, Ning Chen, Xiaochun Cao

Adversarial examples have been demonstrated to threaten many computer vision tasks including object detection. However, the existing attacking methods for object detection have two limitations: poor transferability, whic…

Generative Adversarial NetworkObjectobject-detectionObject Detection+1