Published In
2025 19th International Conference on Semantic Computing (ICSC)
Document Type
Post-Print
Publication Date
2025
Subjects
Machine Learning, Adversarial Attack, Diffusion Model, Denoising Diffusion Probabilistic Models, DDPM, Security, Image Manipulation
Abstract
Diffusion models are becoming an increasingly popular emerging technology, however their use in adversarial attacks remains a scarcely explored topic. We show that diffusion models can be used to create end-to-end hidden adversarial perturbations with high rate of success, and propose a novel diffusion based adversarial attack that allows for substantially faster training time (through improved convergence on high quality images) and with substantially less computational overhead than typical diffusion model training
Rights
© 2025 IEEE
Locate the Document
DOI
10.1109/ICSC64641.2025.00009
Persistent Identifier
https://archives.pdx.edu/ds/psu/44172
Publisher
IEEE
Citation Details
Jalalipour, S., & Rekabdar, B. (2025). OSA-Diff: An Origin Sampling Based Adversarial Attack Using Diffusion Models. 2025 19th International Conference on Semantic Computing (ICSC), 20–27. https://doi.org/10.1109/icsc64641.2025.00009
Description
This is the author’s version of a work that was accepted for publication. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published as: OSA-Diff: An Origin Sampling Based Adversarial Attack Using Diffusion Models. 2025 19th International Conference on Semantic Computing (ICSC), 20–27. https://doi.org/10.1109/icsc64641.2025.00009