Tampere University of Technology

TUTCRIS Research Portal

MLAttack: Fooling Semantic Segmentation Networks by Multi-layer Attacks

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Original languageEnglish
Title of host publicationPattern Recognition - 41st DAGM German Conference, DAGM GCPR 2019, Proceedings
EditorsGernot A. Fink, Simone Frintrop, Xiaoyi Jiang
Number of pages13
ISBN (Print)9783030336752
Publication statusPublished - 2019
Publication typeA4 Article in a conference publication
EventDAGM German Conference on Pattern Recognition - Dortmund, Germany
Duration: 10 Sep 201913 Sep 2019

Publication series

NameLecture Notes in Computer Science
Volume11824 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceDAGM German Conference on Pattern Recognition


Despite the immense success of deep neural networks, their applicability is limited because they can be fooled by adversarial examples, which are generated by adding visually imperceptible and structured perturbations to the original image. Semantic segmentation is required in several visual recognition tasks, but unlike image classification, only a few studies are available for attacking semantic segmentation networks. The existing semantic segmentation adversarial attacks employ different gradient based loss functions which are defined using only the last layer of the network for gradient backpropogation. But some components of semantic segmentation networks implicitly mitigate several adversarial attacks (like multiscale analysis) due to which the existing attacks perform poorly. This provides us the motivation to introduce a new attack in this paper known as MLAttack, i.e., Multiple Layers Attack. It carefully selects several layers and use them to define a loss function for gradient based adversarial attack on semantic segmentation architectures. Experiments conducted on publicly available dataset using the state-of-the-art segmentation network architectures, demonstrate that MLAttack performs better than existing state-of-the-art semantic segmentation attacks.

Publication forum classification

Field of science, Statistics Finland