Universal Adversarial Perturbations Against Semantic Image Segmentation

Metzen, Jan Hendrik; Kumar, Mummadi Chaithanya; Brox, Thomas; Fischer, Volker

doi:10.1109/iccv.2017.300

Cited by 248 publications

(153 citation statements)

References 27 publications

Supporting

Mentioning

151

Contrasting

Order By: Relevance

“…There are also studies on semantic segmentation and object detection models in computer vision (Xie et al, 2017b;Metzen et al, 2017b). In both semantic segmentation and object detection tasks, the goal is to learn a model that associates an input image x with a series of labels Y = {y 1 , y 2 , ...y N }.…”

Section: Object Detection and Semantic Segmentationmentioning

confidence: 99%

“…The work (Xie et al, 2017b) can generate an adversarial perturbation on x which can cause the classifier to give wrong prediction on all the output labels of the model, in order to fool either semantic segmentation or object detection models. The work (Metzen et al, 2017b) finds that there exists universal perturbation for any input image for semantic segmentation models.…”

Section: Object Detection and Semantic Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Liu

et al. 2020

Int. J. Autom. Comput.

519

215

View full text Add to dashboard Cite

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i.e., images, graphs and text.

show abstract

Section: Object Detection and Semantic Segmentationmentioning

confidence: 99%

Section: Object Detection and Semantic Segmentationmentioning

confidence: 99%

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Liu

et al. 2020

Int. J. Autom. Comput.

519

215

View full text Add to dashboard Cite

show abstract

“…outline the "attack generator". • We validate our conceptual ideas by investigating the semantic segmentation adversarial attacks introduced in [27]. Furthermore, we present first small experiments, where we deduce new attacks by exchanging various measures of the original attack formulations.…”

Section: Introductionmentioning

confidence: 73%

“…For example, the perturbation always forces the victim model to output one fixed image of an empty street without any pedestrians or cars in sight. • Dynamic Target: This type of goal has also been introduced by Metzen et al [27] in the context of attacking semantic image segmentation. Here, the adversarial perturbation aims at keeping the ML module's output unchanged with the exception of removing certain target classes.…”

Section: Adversary's Goalsmentioning

confidence: 99%

The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks

Assion¹,

Schlicht

GreBner³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Most state-of-the-art machine learning (ML) classification systems are vulnerable to adversarial perturbations. As a consequence, adversarial robustness poses a significant challenge for the deployment of ML-based systems in safety-and security-critical environments like autonomous driving, disease detection or unmanned aerial vehicles. In the past years we have seen an impressive amount of publications presenting more and more new adversarial attacks. However, the attack research seems to be rather unstructured and new attacks often appear to be random selections from the unlimited set of possible adversarial attacks. With this publication, we present a structured analysis of the adversarial attack creation process. By detecting different building blocks of adversarial attacks, we outline the road to new sets of adversarial attacks. We call this the "attack generator". In the pursuit of this objective, we summarize and extend existing adversarial perturbation taxonomies. The resulting taxonomy is then linked to the application context of computer vision systems for autonomous vehicles, i.e. semantic segmentation and object detection. Finally, in order to prove the usefulness of the attack generator, we investigate existing semantic segmentation attacks with respect to the detected defining components of adversarial attacks.

show abstract

“…ignoring pedes-trians on street). Metzen et al [11] proposed to generate adversarial examples so that the segmentation model incorrectly segments one cityscape as another one.…”

Section: Related Workmentioning

confidence: 99%

Intelligent Image Synthesis to Attack a Segmentation CNN Using Adversarial Learning

Chen

Bentley

Mori

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Deep learning approaches based on convolutional neural networks (CNNs) have been successful in solving a number of problems in medical imaging, including image segmentation. In recent years, it has been shown that CNNs are vulnerable to attacks in which the input image is perturbed by relatively small amounts of noise so that the CNN is no longer able to perform a segmentation of the perturbed image with sufficient accuracy. Therefore, exploring methods on how to attack CNN-based models as well as how to defend models against attacks have become a popular topic as this also provides insights into the performance and generalization abilities of CNNs. However, most of the existing work assumes unrealistic attack models, i.e. the resulting attacks were specified in advance. In this paper, we propose a novel approach for generating adversarial examples to attack CNN-based segmentation models for medical images. Our approach has three key features: 1) The generated adversarial examples exhibit anatomical variations (in form of deformations) as well as appearance perturbations; 2) The adversarial examples attack segmentation models so that the Dice scores decrease by a pre-specified amount; 3) The attack is not required to be specified beforehand. We have evaluated our approach on CNN-based approaches for the multi-organ segmentation problem in 2D CT images. We show that the proposed approach can be used to attack different CNN-based segmentation models.

show abstract

Universal Adversarial Perturbations Against Semantic Image Segmentation

Cited by 248 publications

References 27 publications

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks

Intelligent Image Synthesis to Attack a Segmentation CNN Using Adversarial Learning

Contact Info

Product

Resources

About