# Adversarial Detection: Attacking Object Detection in Real Time

Source: [Adversarial Detection: Attacking Object Detection in Real Time](<https://www.sota2.com/research/paper/68fa717a1e209131cea517e9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:07:38.985Z

Authors: Han Wu, Syed Yunas, Sareh Rowlands, Wenjie Ruan, Johan Wahlstrom

Published: 2022-09-05T13:32:41.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2209.01962>)

[PDF](<https://arxiv.org/pdf/2209.01962.pdf>)