1 code implementation • 3 Nov 2023 • Vasu Singla, Pedro Sandoval-Segura, Micah Goldblum, Jonas Geiping, Tom Goldstein
Our approach serves as a simple and efficient baseline for data attribution on images.
1 code implementation • NeurIPS 2023 • Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein
While it is widely believed that duplicated images in the training set are responsible for content replication at inference time, we observe that the text conditioning of the model plays a similarly important role.
1 code implementation • NeurIPS 2023 • Pedro Sandoval-Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein
First, it is widely believed that neural networks trained on unlearnable datasets only learn shortcuts, simpler rules that are not useful for generalization.
no code implementations • CVPR 2023 • Gowthami Somepalli, Vasu Singla, Micah Goldblum, Jonas Geiping, Tom Goldstein
Cutting-edge diffusion models produce images with high quality and customizability, enabling them to be used for commercial art and graphic design purposes.
2 code implementations • 8 Jun 2022 • Pedro Sandoval-Segura, Vasu Singla, Jonas Geiping, Micah Goldblum, Tom Goldstein, David W. Jacobs
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.
no code implementations • 19 Apr 2022 • Pedro Sandoval-Segura, Vasu Singla, Liam Fowl, Jonas Geiping, Micah Goldblum, David Jacobs, Tom Goldstein
We advocate for evaluating poisons in terms of peak test accuracy.
1 code implementation • NeurIPS 2021 • Songwei Ge, Vasu Singla, Ronen Basri, David Jacobs
Using this, we prove that shift invariance in neural networks produces adversarial examples for the simple case of two classes, each consisting of a single image with a black or white dot on a gray background.
1 code implementation • ICCV 2021 • Vasu Singla, Sahil Singla, David Jacobs, Soheil Feizi
In particular, we show that using activation functions with low (exact or approximate) curvature values has a regularization effect that significantly reduces both the standard and robust generalization gaps in adversarial training.
1 code implementation • 19 Jul 2020 • Rohun Tripathi, Vasu Singla, Mahyar Najibi, Bharat Singh, Abhishek Sharma, Larry Davis
The widely adopted sequential variant of Non Maximum Suppression (or Greedy-NMS) is a crucial module for object-detection pipelines.