EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation

Yifan Wu, Jiawei Du, Ping Liu, Yuewei Lin, Wei Xu, Wenqing Cheng

IEEE Transactions on Image Processing · 2025 · 34 · 2052-2066

DOI: 10.1109/tip.2025.3553786 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Yifan Wu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dataset distillation techniques have revolutionized the way of utilizing large datasets by compressing them into smaller, yet highly effective subsets that preserve the original datasets' accuracy. However, while these methods have proven effective in reducing data size and training times, the robustness of these distilled datasets against adversarial attacks remains underexplored. This vulnerability poses significant risks, particularly in security-sensitive applications. To address this critical gap, we introduce DD-RobustBench, a novel and comprehensive benchmark specifically designed to evaluate the adversarial robustness of distilled datasets. Our benchmark is the most extensive of its kind and integrates a variety of dataset distillation techniques, including recent advancements such as TESLA, DREAM, SRe2L, and D4M, which have shown promise in enhancing model performance. DD-RobustBench also rigorously tests these datasets against a diverse array of adversarial attack methods to ensure broad applicability. Our evaluations cover a wide spectrum of datasets, including but not limited to, the widely used ImageNet-1K. This allows us to assess the robustness of distilled datasets in scenarios mirroring real-world applications. Furthermore, our detailed quantitative analysis investigates how different components involved in the distillation process, such as data augmentation, downsampling, and clustering, affect dataset robustness. Our findings provide critical insights into which techniques enhance or weaken the resilience of distilled datasets against adversarial threats, offering valuable guidelines for developing more robust distillation methods in the future. Through DD-RobustBench, we aim not only to benchmark but also to push the boundaries of dataset distillation research by highlighting areas for improvement and suggesting pathways for future innovations in creating datasets that are not only compact and efficient but also secure and resilient to adversarial challenges. The implementation details and essential instructions are available on DD-RobustBench.

Zitieren

APA

Wu, Y., Du, J., Liu, P., Lin, Y., Xu, W., & Cheng, W. (2025). DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation. IEEE Transactions on Image Processing, 34, 2052-2066. https://doi.org/10.1109/tip.2025.3553786

Vancouver

Wu Y, Du J, Liu P, Lin Y, Xu W, Cheng W. DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation. IEEE Transactions on Image Processing. 2025;34:2052-2066. doi:10.1109/tip.2025.3553786

BibTeX
@article{Wu2025,
  author = {Wu, Yifan and Du, Jiawei and Liu, Ping and Lin, Yuewei and Xu, Wei and Cheng, Wenqing},
  title = {DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation},
  journal = {IEEE Transactions on Image Processing},
  year = {2025},
  volume = {34},
  pages = {2052--2066},
  doi = {10.1109/tip.2025.3553786}
}
Kostenlos starten →