Certified Patch Robustness via Smoothed Vision Transformers-Reference-Cited by-同舟云学术

Certified Patch Robustness via Smoothed Vision Transformers

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:

Salman Hadi¹,Jain Saachi¹,Wong Eric¹,Madry Aleksander¹

Affiliation:

1. MIT

Funder

NSF

Defense Advanced Research Projects Agency (DARPA)

Publisher

IEEE

Link

Reference63 articles.

1. Adversarial training against location-optimized adversarial patches;rao;ArXiv Preprint,2020

3. Differentiable abstract interpretation for provably robust neural networks;mirman;International Conference on Machine Learning (ICML),0

4. Efficient certified defenses against patch attacks on image classifiers;metzen;International Conference on Learning Representations,0

5. An approach to reachability analysis for feed-forward relu neural networks;lomuscio;ArXiv Preprint,2017

Cited by 12 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

2. A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Models;2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE);2023-09-11

3. Defending Against Universal Patch Attacks by Restricting Token Attention in Vision Transformers;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

4. Jedi: Entropy-Based Localization and Removal of Adversarial Patches;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06