Provable Adversarial Defense
3 papers with code • 2 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Provable Adversarial Defense
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
CIFAR-10
CIFAR-100
Most implemented papers
Certified Defense to Image Transformations via Randomized Smoothing
eth-sri/transformation-smoothing
•
•
NeurIPS 2020
We extend randomized smoothing to cover parameterized transformations (e. g., rotations, translations) and certify robustness in the parameter space (e. g., rotation angle).
Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting
harrywuhust2022/Adv-Crowd-analysis
•
•
Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems.
A Unified Algebraic Perspective on Lipschitz Neural Networks
araujoalexandre/lipschitz-sll-networks
•
•
ICLR 2023
Important research efforts have focused on the design and training of neural networks with a controlled Lipschitz constant.
