adversarial-1

Provable Adversarial Defense

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in provable-adversarial-defense-1

Trend

Dataset

Best Model

Actions

CIFAR-10

CIFAR-100

Libraries

i

Use these libraries to find provable-adversarial-defense-1 models and implementations

Datasets

CIFAR-10

CIFAR-100

Subtasks

No subtasks available.

Most implemented papers

Certified Defense to Image Transformations via Randomized Smoothing

Martin T. Vechev, Marc Fischer, Maximilian Baader•Wed Feb 26 2020

This work extends randomized smoothing to cover parameterized transformations and certify robustness in the parameter space and shows how to efficiently compute the inverse of an image transformation, enabling individual guarantees in the online setting.

73

Content

0

Paper Graph

Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting

Pan Zhou, Xiaoqing Ye, Binghui Wang, Qiming Wu, Zhikang Zou, Ang Li•Wed Apr 21 2021

This work proposes a robust attack strategy called Adversarial Patch Attack with Momentum (APAM) to systematically evaluate the robustness of crowd counting models, where the attacker's goal is to create an adversarial perturbation that severely degrades their performances, thus leading to public safety accidents.

8 0

Paper Graph

A Unified Algebraic Perspective on Lipschitz Neural Networks

A. Allauzen, Alexandre Araujo, Aaron J. Havens, Blaise Delattre, Bin Hu•Sun Mar 05 2023

A novel algebraic perspective unifies various types of 1-Lipschitz neural networks, including the ones previously mentioned, along with methods based on orthogonality and spectral methods, and shows that SLLs outperform previous approaches on certified robust accuracy.

65 0

Paper Graph

Adding a benchmark result helps the community track progress.