Dec 12, 2023
How Training Data Guides Diffusion Models
We introduce a new framework for data attribution in generative settings, and propose an efficient method to attribute diffusion models.
Jul 20, 2023
Rethinking Backdoor Attacks
We introduce a new perspective on backdoor attacks and defenses in deep learning.
Mar 27, 2023
TRAK-ing Model Behavior with Data
We introduce TRAK, a new data attribution method that scales to large(r) models!
Feb 16, 2023
Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation
We introduce dataset interfaces, a scalable framework that synthesizes counterfactual examples under user-specified shifts
Dec 14, 2022
Tailored Data Augmentation to Mitigate Model Failures
We demonstrate how we can use Stable Diffusion to target a model's failure modes
Nov 23, 2022
ModelDiff: A Framework for Comparing Learning Algorithms
We introduce a framework for comparing ML models trained with different learning algorithms.
Nov 3, 2022
Raising the Cost of Malicious AI-Powered Image Editing
Inspired by an episode of the Daily Show, we hacked together a technique for "immunizing" images against being edited by diffusion models.
Jul 12, 2022
A Data-Based Perspective on Transfer Learning
We present a framework for pinpointing the impact of the source datasets in transfer learning.
