# Adversarial Examples for Semantic Image Segmentation

Source: [Adversarial Examples for Semantic Image Segmentation](<https://www.sota2.com/research/paper/68fa63331e209131ce9fd5ca>)

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

Data updated: 2025-10-25T20:35:17.063Z

Authors: Volker Fischer, Mummadi Chaithanya Kumar, Jan Hendrik Metzen, Thomas Brox

Published: 2017-03-03T10:27:16.000Z

## Abstract

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this contribution, we analyse how adversarial perturbations can affect the task of semantic segmentation. We show how existing adversarial attackers can be transferred to this task and that it is possible to create imperceptible adversarial perturbations that lead a deep network to misclassify almost all pixels of a chosen class while leaving network prediction nearly unchanged outside this class.

## 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/1703.01101>)

[PDF](<https://arxiv.org/pdf/1703.01101.pdf>)