# Exploring the Space of Adversarial Images

Source: [Exploring the Space of Adversarial Images](<https://www.sota2.com/research/paper/68fa629d1e209131ce9fa389>)

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

Data updated: 2025-10-25T20:22:26.903Z

Authors: Pedro Tabacof, Eduardo Valle

Published: 2015-10-19T00:54:37.000Z

## Abstract

Adversarial examples have raised questions regarding the robustness and security of deep neural networks. In this work we formalize the problem of adversarial images given a pretrained classifier, showing that even in the linear case the resulting optimization problem is nonconvex. We generate adversarial images using shallow and deep classifiers on the MNIST and ImageNet datasets. We probe the pixel space of adversarial images using noise of varying intensity and distribution. We bring novel visualizations that showcase the phenomenon and its high variability. We show that adversarial images appear in large regions in the pixel space, but that, for the same task, a shallow classifier seems more robust to adversarial images than a deep convolutional network.

## 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/1510.05328>)

[PDF](<https://arxiv.org/pdf/1510.05328.pdf>)