Adversarial Detection: Attacking Object Detection in Real Time

09/05/2022
by   Han Wu, et al.
0

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 about 20 iterations. The demo video is available at: https://youtu.be/zJZ1aNlXsMU.

READ FULL TEXT

page 1

page 2

page 4

research
08/15/2022

Man-in-the-Middle Attack against Object Detection Systems

Is deep learning secure for robots? As embedded systems have access to m...
research
01/12/2020

Membership Inference Attacks Against Object Detection Models

Machine learning models can leak information about the dataset they trai...
research
04/11/2023

Overload: Latency Attacks on Object Detection for Edge Devices

Nowadays, the deployment of deep learning based applications on edge dev...
research
07/10/2014

ARTOS -- Adaptive Real-Time Object Detection System

ARTOS is all about creating, tuning, and applying object detection model...
research
11/07/2021

Natural Adversarial Objects

Although state-of-the-art object detection methods have shown compelling...
research
03/03/2018

Real-Time Deep Learning Method for Abandoned Luggage Detection in Video

Recent terrorist attacks in major cities around the world have brought m...
research
08/19/2020

CCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection

Deep neural network based object detection hasbecome the cornerstone of ...

Please sign up or login with your details

Forgot password? Click here to reset