CRFL: Certifiably Robust Federated Learning against Backdoor Attacks (ICML 2021)
-
Updated
Aug 5, 2021 - Python
CRFL: Certifiably Robust Federated Learning against Backdoor Attacks (ICML 2021)
Robustify Black-Box Models (ICLR'22 - Spotlight)
[NeurIPS 2021] Fast Certified Robust Training with Short Warmup
[ICLR 2022] Training L_inf-dist-net with faster acceleration and better training strategies
Official implementation of the paper "PromptSmooth: Certifying Robustness of Medical Vision-Language Models via Prompt Learning"
Keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on popular datasets
[ICLR 2022] Boosting Randomized Smoothing with Variance Reduced Classifiers
Implementation of Boosting Certified $\ell_\infty$-dist Robustness with EMA Method and Ensemble Model
[NeurIPS 2022] (De-)Randomized Smoothing for Decision Stump Ensembles
[SRML@ICLR 2022] Robust and Accurate -- Compositional Architectures for Randomized Smoothing
Add a description, image, and links to the certified-robustness topic page so that developers can more easily learn about it.
To associate your repository with the certified-robustness topic, visit your repo's landing page and select "manage topics."