Adversarial Examples are Misaligned in Diffusion Model Manifolds
- In recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results. Nevertheless, the versatility of these models extends beyond their generative capabilities to encompass various vision applications, such as image inpainting, segmentation, adversarial robustness, among others. This study isIn recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results. Nevertheless, the versatility of these models extends beyond their generative capabilities to encompass various vision applications, such as image inpainting, segmentation, adversarial robustness, among others. This study is dedicated to the investigation of adversarial attacks through the lens of diffusion models. However, our objective does not involve enhancing the adversarial robustness of image classifiers. Instead, our focus lies in utilizing the diffusion model to detect and analyze the anomalies introduced by these attacks on images. To that end, we systematically examine the alignment of the distributions of adversarial examples when subjected to the process of transformation using diffusion models. The efficacy of this approach is assessed across CIFAR-10 and ImageNet datasets, including varying image sizes in the latter. The results demonstrate a notable capacity to discriminate effectively between benign and attacked images, providing compelling evidence that adversarial instances do not align with the learned manifold of the DMs.…


| Dokumentart: | Konferenzveröffentlichung |
|---|---|
| Art der Konferenzveröffentlichung: | Konferenzartikel |
| Zitierlink: | https://opus.hs-offenburg.de/10019 | Bibliografische Angaben |
| Titel (Englisch): | Adversarial Examples are Misaligned in Diffusion Model Manifolds |
| Konferenzangaben: | International Joint Conference on Neural Networks (30 June - 05 July 2024 : Yokohama, Japan) |
| Verfasserangaben: | Peter Lorenz, Ricard Durall Lopez, Janis KeuperStaff MemberORCiDGND |
| Erscheinungsjahr: | 2024 |
| Verlag: | IEEE |
| Erste Seite: | 1 |
| Letzte Seite: | 8 |
| Titel des übergeordneten Werkes (Englisch): | IJCNN 2024 : Conference Proceedings |
| ISBN: | 979-8-3503-5931-2 (Elektronisch) |
| ISBN: | 979-8-3503-5932-9 (Print on Demand) |
| ISSN: | 2161-4407 (Elektronisch) |
| ISSN: | 2161-4393 (Print on Demand) |
| DOI: | https://doi.org/10.1109/IJCNN60899.2024.10650024 |
| Sprache: | Englisch | Inhaltliche Informationen |
| Fakultäten / Einrichtungen: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
| Forschung: | IMLA - Institute for Machine Learning and Analytics |
| Sammlungen der Hochschule Offenburg: | Bibliografie |
| Freies Schlagwort / Tag: | Deep learning Image segmentation; Manifolds; Neural networks | Formale Angaben |
| Relevanz für "Jahresbericht über Forschungsleistungen": | 5-fach | Konferenzbeitrag |
| Open-Access-Status: | Closed |
| Lizenz (Deutsch): | Urheberrechtlich geschützt |



