Towards Practical Certifiable Patch Defense with Vision Transformer-Reference-Cited by-同舟云学术

Towards Practical Certifiable Patch Defense with Vision Transformer

Published:2022-06 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Chen Zhaoyu¹,Li Bo²,Xu Jianghe²,Wu Shuang²,Ding Shouhong²,Zhang Wenqiang¹

Affiliation:

1. Academy for Engineering and Technology, Fudan University

2. Tencent Youtu Lab

Funder

National Natural Science Foundation of China

National Key R&D Program of China

Shanghai Science and Technology Committee

Publisher

IEEE

Link

Reference45 articles.

1. Patchguard: Provable defense against adversarial patches using masks on small receptive fields;xiang;CoRR,2020

2. Making an invisibility cloak: Real world adversarial attacks on object detectors;wu;Computer Vision - ECCV 2020 – 16th European Conference,2020

3. Intriguing properties of neural networks;szegedy;2nd International Conference on Learning Representations ICLR 2014,2014

Cited by 41 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

4. RDAT: an efficient regularized decoupled adversarial training mechanism;International Journal of Multimedia Information Retrieval;2024-05-07

5. Architecture-Agnostic Iterative Black-Box Certified Defense Against Adversarial Patches;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14