Search Results for author:
Found 2 papers, 1 papers with code
Defending Against Universal Adversarial Patches by Clipping Feature Norms
Physical-world adversarial attacks based on universal adversarial patches have been proved to be able to mislead deep convolutional neural networks (CNNs), exposing the vulnerability of real-world visual classification systems based on CNNs.
Sparse Adversarial Attack to Object Detection
Many adversarial attacks have been proposed to attack image classifiers, but few work shift attention to object detectors.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
