# Fooling Object Detectors: Adversarial Attacks by Half-Neighbor Masks

Source: [Fooling Object Detectors: Adversarial Attacks by Half-Neighbor Masks](<https://www.sota2.com/research/paper/68fa69101e209131cea1fea3>)

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

Data updated: 2025-10-25T22:52:51.647Z

Authors: Yanghao Zhang, Fu Wang, Wenjie Ruan

Published: 2021-01-04T14:03:22.000Z

## Abstract

Although there are a great number of adversarial attacks on deep learning based classifiers, how to attack object detection systems has been rarely studied. In this paper, we propose a Half-Neighbor Masked Projected Gradient Descent (HNM-PGD) based attack, which can generate strong perturbation to fool different kinds of detectors under strict constraints. We also applied the proposed HNM-PGD attack in the CIKM 2020 AnalytiCup Competition, which was ranked within the top 1% on the leaderboard. We release the code at https://github.com/YanghaoZYH/HNM-PGD.

## 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/2101.00989>)

[PDF](<https://arxiv.org/pdf/2101.00989.pdf>)
