DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation

arXiv:2403.13322v1 Announce Type: new
Abstract: Dataset distillation is an advanced technique aimed at compressing datasets into significantly smaller counterparts, while preserving formidable training performance. Significant efforts have been devoted to promote evaluation accuracy under limited compression ratio while overlooked the robustness of distilled dataset. In this work, we introduce a comprehensive benchmark that, to the best of our knowledge, is the most extensive to date for evaluating the adversarial robustness of distilled datasets in a unified way. Our benchmark significantly …

abstract accuracy advanced adversarial arxiv benchmark compression cs.cv dataset datasets distillation evaluation performance promote robustness training type work