Meaod: Model extraction attack against object detectors

Z Li, C Shi, Y Pu, X Zhang, Y Li, J Li, S Ji - arXiv preprint arXiv:2312.14677, 2023 - arxiv.org
The widespread use of deep learning technology across various industries has made deep
neural network models highly valuable and, as a result, attractive targets for potential …

Stealing Image-to-Image Translation Models With a Single Query

N Spingarn-Eliezer, T Michaeli - arXiv preprint arXiv:2406.00828, 2024 - arxiv.org
Training deep neural networks requires significant computational resources and large
datasets that are often confidential or expensive to collect. As a result, owners tend to protect …