# Sparse Adversarial Attack to Object Detection

Source: [Sparse Adversarial Attack to Object Detection](<https://www.sota2.com/research/paper/68fa68fe1e209131cea1fa03>)

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

Data updated: 2025-10-25T22:51:52.067Z

Authors: Jiayu Bao

Published: 2020-12-26T07:52:28.000Z

## Abstract

Adversarial examples have gained tons of attention in recent years. Many adversarial attacks have been proposed to attack image classifiers, but few work shift attention to object detectors. In this paper, we propose Sparse Adversarial Attack (SAA) which enables adversaries to perform effective evasion attack on detectors with bounded \\emph{l$\_{0}$} norm perturbation. We select the fragile position of the image and designed evasion loss function for the task. Experiment results on YOLOv4 and FasterRCNN reveal the effectiveness of our method. In addition, our SAA shows great transferability across different detectors in the black-box attack setting. Codes are available at \\emph{https://github.com/THUrssq/Tianchi04}.

## 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/2012.13692>)

[PDF](<https://arxiv.org/pdf/2012.13692.pdf>)
