keyword

adversarial example

An adversarial example is an input to a machine learning model that has been intentionally crafted or modified to cause the algorithm to make an incorrect prediction or classification. These perturbations can range from subtle, nearly imperceptible digital modifications to visible, localized physical patterns designed to mislead automated systems while remaining understandable or innocuous to humans. Adversarial examples exploit vulnerabilities in the mathematical decision boundaries of deep neural networks and other predictive models, and they can be engineered either to force a specific targeted misclassification or to induce general system failure across both digital pipelines and physical environments.

1 item

Adversarial Patch

Tom B. Brown, Dandelion Mané, Aurko Roy, Martín Abadi, Justin Gilmer

OrganizationsGoogle

Why you should read this

Introduces printable, scene-agnostic adversarial patches capable of overriding deep learning image classifiers in the physical world to force the prediction of an arbitrary target class.

We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety of transformations, and targeted because they can cause a classifier to output any target class. These adversarial patches can be printed, added to any scene, photographed, and presented to image classifiers; even when the patches are small, they cause the classifiers to ignore the other items in the scene and report a chosen target class. To reproduce the results from the paper, our code is available at this https URL

Source

https://arxiv.org/pdf/1712.09665.pdf

Added

2026-09-25