# Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior

Source: [Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior](<https://www.sota2.com/research/paper/68fa65fc1e209131cea0dc0b>)

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

Data updated: 2025-10-25T21:40:30.056Z

Authors: Thomas Gittings, Steve Schneider, John Collomosse

Published: 2019-07-03T15:40:05.000Z

## Abstract

We present a novel method for generating robust adversarial image examples building upon the recent \`deep image prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in image synthesis. Adversarial images are commonly generated by perturbing images to introduce high frequency noise that induces image misclassification, but that is fragile to subsequent digital manipulation of the image. We show that using DIP to reconstruct an image under adversarial constraint induces perturbations that are more robust to affine deformation, whilst remaining visually imperceptible. Furthermore we show that our DIP approach can also be adapted to produce local adversarial patches (\`adversarial stickers'). We demonstrate robust adversarial examples over a broad gamut of images and object classes drawn from the ImageNet dataset.

## 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/1907.01996>)

[PDF](<https://arxiv.org/pdf/1907.01996.pdf>)