Search Results for author:
Found 7 papers, 4 papers with code
A Simple and Efficient Baseline for Data Attribution on Images
Our approach serves as a simple and efficient baseline for data attribution on images.
What Can We Learn from Unlearnable Datasets?
First, it is widely believed that neural networks trained on unlearnable datasets only learn shortcuts, simpler rules that are not useful for generalization.
JPEG Compressed Images Can Bypass Protections Against AI Editing
Recently developed text-to-image diffusion models make it easy to edit or create high-quality images.
Autoregressive Perturbations for Data Poisoning
Unfortunately, existing methods require knowledge of both the target architecture and the complete dataset so that a surrogate network can be trained, the parameters of which are used to generate the attack.
Poisons that are learned faster are more effective
We advocate for evaluating poisons in terms of peak test accuracy.
Adversarially robust segmentation models learn perceptually-aligned gradients
The effects of adversarial training on semantic segmentation networks has not been thoroughly explored.
AutoProtoNet: Interpretability for Prototypical Networks
In meta-learning approaches, it is difficult for a practitioner to make sense of what kind of representations the model employs.
