Show simple item record

dc.contributor.authorSietzen, Stefanen_US
dc.contributor.authorLechner, Mathiasen_US
dc.contributor.authorBorowski, Judyen_US
dc.contributor.authorHasani, Raminen_US
dc.contributor.authorWaldner, Manuelaen_US
dc.contributor.editorZhang, Fang-Lue and Eisemann, Elmar and Singh, Karanen_US
dc.description.abstractWhile convolutional neural networks (CNNs) have found wide adoption as state-of-the-art models for image-related tasks, their predictions are often highly sensitive to small input perturbations, which the human vision is robust against. This paper presents Perturber, a web-based application that allows users to instantaneously explore how CNN activations and predictions evolve when a 3D input scene is interactively perturbed. Perturber offers a large variety of scene modifications, such as camera controls, lighting and shading effects, background modifications, object morphing, as well as adversarial attacks, to facilitate the discovery of potential vulnerabilities. Fine-tuned model versions can be directly compared for qualitative evaluation of their robustness. Case studies with machine learning experts have shown that Perturber helps users to quickly generate hypotheses about model vulnerabilities and to qualitatively compare model behavior. Using quantitative analyses, we could replicate users' insights with other CNN architectures and input images, yielding new insights about the vulnerability of adversarially trained models.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectHuman centered computing
dc.subjectVisualization systems and tools
dc.subjectComputing methodologies
dc.subjectMachine learning
dc.titleInteractive Analysis of CNN Robustnessen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersInteraction and Interfaces

Files in this item


This item appears in the following Collection(s)

  • 40-Issue 7
    Pacific Graphics 2021 - Symposium Proceedings

Show simple item record