11 citations · 15 across the 4 of their papers we have counts for
4 papers
Training Data Attribution for Diffusion Models
Zheng Dai, David K Gifford
Diffusion models have become increasingly popular for synthesizing high-quality samples based on training datasets. However, given the oftentimes enormous sizes of the training dat…
Image classifiers can not be made robust to small perturbations
Zheng Dai, David K. Gifford
The sensitivity of image classifiers to small perturbations in the input is often viewed as a defect of their construction. We demonstrate that this sensitivity is a fundamental pr…
What made you do this? Understanding black-box decisions with sufficient input subsets
Brandon Carter, Jonas Mueller, Siddhartha Jain +1
Local explanation frameworks aim to rationalize particular decisions made by a black-box prediction model. Existing techniques are often restricted to a specific type of predictor…
Modeling Persistent Trends in Distributions
Jonas Mueller, Tommi Jaakkola, David Gifford
We present a nonparametric framework to model a short sequence of probability distributions that vary both due to underlying effects of sequential progression and confounding noise…