Search Results for author:
Found 3 papers, 1 papers with code
Adversarial Attacks on Foundational Vision Models
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)!
SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection
Building up reliable Out-of-Distribution (OOD) detectors is challenging, often requiring the use of OOD data during training.
Active Learning Under Malicious Mislabeling and Poisoning Attacks
To check the performance of the proposed method under an adversarial setting, i. e., malicious mislabeling and data poisoning attacks, we perform an extensive evaluation on the reduced CIFAR-10 dataset, which contains only two classes: airplane and frog.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
