A Comprehensive Study on Dataset Distillation: Performance, Privacy, Robustness and Fairness

Understand

The aim of dataset distillation is to encode the rich features of an original dataset into a tiny dataset.

• It is a promising approach to accelerate neural network training and related studies.
• Different approaches have been proposed to improve the informativeness and generalization performance of distilled images.
• However, no work has comprehensively analyzed this technique from a security perspective and there is a lack of systematic understanding of potential risks.