Search Results for author:
Found 3 papers, 3 papers with code
Understanding the Vulnerability of CLIP to Image Compression
CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks.
Analysing Training-Data Leakage from Gradients through Linear Systems and Gradient Matching
As a result, we are able to partially attribute the leakage of the training data in a deep network to its architecture.
Understanding Training-Data Leakage from Gradients in Neural Networks for Image Classification
Based on this formulation, we are able to attribute the potential leakage of the training data in a deep network to its architecture.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
