Adversarial Examples for Semantic Image Segmentation

By Volker Fischer, Mummadi Chaithanya Kumar, Jan Hendrik Metzen, Thomas Brox. 2017

123 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Mitigating adversarial effects through randomization (2017, background): “, 2017) and semantic segmentation (Xie et al., 2017; Fischer et al., 2017; Cisse et al., 2017).”
Adversarial Examples for Semantic Segmentation and Object Detection (2017, background): “[9] showed the existence of adversarial examples, and [21] showed the existence of universal perturbations.”
Adversarial Examples: Attacks and Defenses for Deep Learning (2017, background): “Similar to [88], pixels that belong to the targeted classes would be assigned to their nearest background classes”
Universal Adversarial Perturbations Against Semantic Image Segmentation (2017, methodology): “Concurrent with this work, adversarial examples have been extended to semantic image segmentation and object detection [27, 8].”
Disentangling Adversarial Robustness and Generalization (2018, neutral): “, [27, 18, 98, 49, 37, 56, 2, 16].”
Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples (2019, methodology): “This paper’s focus is evasion attacks which have been proposed against supervised ML algorithms used for image classification [13, 18, 24, 45, 97, 114], object detection [26, 83, 127], image segmentation [6, 41], speech recognition [19, 133] as well as other tasks [27, 48, 65, 129]; generative model”
On the Robustness of Semantic Segmentation Models to Adversarial Attacks (2017, background): “(6) The aforementioned attacks were all proposed in the context of image classification, but they have been adapted to the problems of semantic segmentation [26, 16], object detection [66] and visual question answering [68].”
SegDiff: Image Segmentation with Diffusion Probabilistic Models (2021, background): “While adversarial methods have been attempted [12, 33, 49, 51], they do not constitute the current state of the art.”
Can you fool AI with adversarial examples on a visual Turing test? (2017, background): “While most previous works focus on image classification models, a new line of research studies adversarial examples against deep neural networks for other tasks, such as recurrent neural networks for text processing [43], [20], deep reinforcement learning models for game playing [29], [19], [24], se”
Fooling Vision and Language Models Despite Localization and Attention Mechanism (2017, background): “Another line of research studies adversarial examples against deep neural networks for other tasks, such as recurrent neural networks for text processing [59, 28], deep reinforcement learning models for game playing [41, 26, 34], semantic segmentation [14, 70], and object detection [24, 70].”
Towards Robust CNN-based Object Detection through Augmentation with Synthetic Rain Variations (2019, background): “However, the augmentation techniques used in [17], [22], [24]–[26] are not proven to be realistic and lack a comparison against disturbances from real life scenes.”