# Universal Adversarial Perturbations: Efficiency on a small image dataset

Source: [Universal Adversarial Perturbations: Efficiency on a small image dataset](<https://www.sota2.com/research/paper/68fa6da41e209131cea3b1b8>)

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

Data updated: 2025-10-27T06:17:30.291Z

Authors: Waris Radji

Published: 2022-10-10T11:51:42.000Z

## Abstract

Although neural networks perform very well on the image classification task, they are still vulnerable to adversarial perturbations that can fool a neural network without visibly changing an input image. A paper has shown the existence of Universal Adversarial Perturbations which when added to any image will fool the neural network with a very high probability. In this paper we will try to reproduce the experience of the Universal Adversarial Perturbations paper, but on a smaller neural network architecture and training set, in order to be able to study the efficiency of the computed perturbation.

## 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/2210.04591>)

[PDF](<https://arxiv.org/pdf/2210.04591.pdf>)