Search Results for author: Gwendolyn McDonald

Found 1 papers, 0 papers with code

Adversarial Attacks on Foundational Vision Models

no code implementations28 Aug 2023 Nathan Inkawhich, Gwendolyn McDonald, Ryan Luley

We show our attacks to be potent in whitebox and blackbox settings, as well as when transferred across foundational model types (e. g., attack DINOv2 with CLIP)!

Cannot find the paper you are looking for? You can Submit a new open access paper.