Factory > Showcase > Universal
Name:
Universal
Description:
Universal adversarial perturbations
Professor — Lab:
Pascal Frossard — Signal Processing Laboratory
Technical description:
Proposing a universal (image-agnostic) and very small perturbation vector that causes natural images to be misclassified with high probability in a deep neuronal network.
Papers:
Project status:
inactive — entered showcase: 2019-03-18 — entry updated: 2024-03-21
Source code:
Lab GitHub - last commit: 2017-10-23
Code quality:
This project has not yet been evaluated by the C4DT Factory team. We will be happy to evaluate it upon request.
Project type:
Application
Programming language:
MATLAB, Python