research
∙
05/30/2023
What Can We Learn from Unlearnable Datasets?
In an era of widespread web scraping, unlearnable dataset methods have t...
share
research
∙
04/05/2023
JPEG Compressed Images Can Bypass Protections Against AI Editing
Recently developed text-to-image diffusion models make it easy to edit o...
research
∙
06/08/2022
Autoregressive Perturbations for Data Poisoning
The prevalence of data scraping from social media as a means to obtain d...
research
∙
04/19/2022
Poisons that are learned faster are more effective
Imperceptible poisoning attacks on entire datasets have recently been to...
research
∙
04/03/2022
Adversarially robust segmentation models learn perceptually-aligned gradients
The effects of adversarial training on semantic segmentation networks ha...
research
∙
04/02/2022
AutoProtoNet: Interpretability for Prototypical Networks
In meta-learning approaches, it is difficult for a practitioner to make ...
research
∙
10/12/2020
An Information-Theoretic Perspective on Overfitting and Underfitting
We present an information-theoretic framework for understanding overfitt...
research
∙
12/23/2019