Robust NAS under adversarial training: benchmark, theory, and beyond
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914721063501824 |
|---|---|
| author | Wu, Yongtao Liu, Fanghui Simon-Gabriel, Carl-Johann Chrysos, Grigorios G Cevher, Volkan |
| author_facet | Wu, Yongtao Liu, Fanghui Simon-Gabriel, Carl-Johann Chrysos, Grigorios G Cevher, Volkan |
| contents | Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robust architectures, especially when adversarial training is considered. In this work, we aim to address these two challenges, making twofold contributions. First, we release a comprehensive data set that encompasses both clean accuracy and robust accuracy for a vast array of adversarially trained networks from the NAS-Bench-201 search space on image datasets. Then, leveraging the neural tangent kernel (NTK) tool from deep learning theory, we establish a generalization theory for searching architecture in terms of clean accuracy and robust accuracy under multi-objective adversarial training. We firmly believe that our benchmark and theoretical insights will significantly benefit the NAS community through reliable reproducibility, efficient assessment, and theoretical foundation, particularly in the pursuit of robust architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13134 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Robust NAS under adversarial training: benchmark, theory, and beyond Wu, Yongtao Liu, Fanghui Simon-Gabriel, Carl-Johann Chrysos, Grigorios G Cevher, Volkan Machine Learning Artificial Intelligence Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robust architectures, especially when adversarial training is considered. In this work, we aim to address these two challenges, making twofold contributions. First, we release a comprehensive data set that encompasses both clean accuracy and robust accuracy for a vast array of adversarially trained networks from the NAS-Bench-201 search space on image datasets. Then, leveraging the neural tangent kernel (NTK) tool from deep learning theory, we establish a generalization theory for searching architecture in terms of clean accuracy and robust accuracy under multi-objective adversarial training. We firmly believe that our benchmark and theoretical insights will significantly benefit the NAS community through reliable reproducibility, efficient assessment, and theoretical foundation, particularly in the pursuit of robust architectures. |
| title | Robust NAS under adversarial training: benchmark, theory, and beyond |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.13134 |