Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning-Reference-Cited by-同舟云学术

Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning

Published:2023-10-01 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF International Conference on Computer Vision (ICCV)
language:
Short-container-title:

Author:

Zhu Kaijie¹,Hu Xixu²,Wang Jindong³,Xie Xing³,Yang Ge¹

Affiliation:

1. University of Chinese Academy of Sciences,School of Artifical Intelligence

2. City University of Hong Kong

3. Microsoft Research

Funder

Chinese Academy of Sciences

Publisher

IEEE

Link

Reference59 articles.

1. Better fine-tuning by reducing representational collapse;Aghajanyan

2. A closer look at memorization in deep networks;Arpit

3. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples;Athalye

4. Language models are few-shot learners;Brown;Advances in Neural Information Processing Systems,2020

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

5. A Survey of Harnessing Self-Supervision Against Adversarial Attacks;2023 9th International Conference on Computer and Communications (ICCC);2023-12-08