Saved in:
Bibliographic Details
Main Authors: Bagley, Harrison, Meakin, Will, Lucey, Simon, Law, Yee Wei, Chin, Tat-Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.18656
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909920232734720
author Bagley, Harrison
Meakin, Will
Lucey, Simon
Law, Yee Wei
Chin, Tat-Jun
author_facet Bagley, Harrison
Meakin, Will
Lucey, Simon
Law, Yee Wei
Chin, Tat-Jun
contents Physical adversarial attacks on deep learning systems is concerning due to the ease of deploying such attacks, usually by placing an adversarial patch in a scene to manipulate the outcomes of a deep learning model. Training such patches typically requires regularization that improves physical realizability (e.g., printability, smoothness) and/or robustness to real-world variability (e.g. deformations, viewing angle, noise). One type of variability that has received little attention is scale variability. When a patch is rescaled, either digitally through downsampling/upsampling or physically through changing imaging distances, interpolation-induced color mixing occurs. This smooths out pixel values, resulting in a loss of high-frequency patterns and degrading the adversarial signal. To address this, we present a novel superpixel-based regularization method that guides patch optimization to scale-resilient structures. Our ap proach employs the Simple Linear Iterative Clustering (SLIC) algorithm to dynamically cluster pixels in an adversarial patch during optimization. The Implicit Function Theorem is used to backpropagate gradients through SLIC to update the superpixel boundaries and color. This produces patches that maintain their structure over scale and are less susceptible to interpolation losses. Our method achieves greater performance in the digital domain, and when realized physically, these performance gains are preserved, leading to improved physical performance. Real-world performance was objectively assessed using a novel physical evaluation protocol that utilizes screens and cardboard cut-outs to systematically vary real-world conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18656
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Physical Adversarial Patches Using Dynamically Optimized Clusters
Bagley, Harrison
Meakin, Will
Lucey, Simon
Law, Yee Wei
Chin, Tat-Jun
Computer Vision and Pattern Recognition
Physical adversarial attacks on deep learning systems is concerning due to the ease of deploying such attacks, usually by placing an adversarial patch in a scene to manipulate the outcomes of a deep learning model. Training such patches typically requires regularization that improves physical realizability (e.g., printability, smoothness) and/or robustness to real-world variability (e.g. deformations, viewing angle, noise). One type of variability that has received little attention is scale variability. When a patch is rescaled, either digitally through downsampling/upsampling or physically through changing imaging distances, interpolation-induced color mixing occurs. This smooths out pixel values, resulting in a loss of high-frequency patterns and degrading the adversarial signal. To address this, we present a novel superpixel-based regularization method that guides patch optimization to scale-resilient structures. Our ap proach employs the Simple Linear Iterative Clustering (SLIC) algorithm to dynamically cluster pixels in an adversarial patch during optimization. The Implicit Function Theorem is used to backpropagate gradients through SLIC to update the superpixel boundaries and color. This produces patches that maintain their structure over scale and are less susceptible to interpolation losses. Our method achieves greater performance in the digital domain, and when realized physically, these performance gains are preserved, leading to improved physical performance. Real-world performance was objectively assessed using a novel physical evaluation protocol that utilizes screens and cardboard cut-outs to systematically vary real-world conditions.
title Robust Physical Adversarial Patches Using Dynamically Optimized Clusters
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.18656