SOTAVerified

Adversarial Purification

A class of adversarial defense methods that remove adversarial perturbations using a generative model.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 41–50 of 65 papers

TitleStatusHype
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective—0
Adversarial purification for no-reference image-quality metrics: applicability study and new methods—0
Robust Diffusion Models for Adversarial Purification—0
Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSMCode0
PCLD: Point Cloud Layerwise Diffusion for Adversarial PurificationCode0
Adversarial Purification and Fine-tuning for Robust UDC Image Restoration—0
Adversarial Text Purification: A Large Language Model Approach for Defense—0
PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks—0
MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model—0
Adversarial Purification of Information MaskingCode0
Show:102550
← PrevPage 5 of 7Next →

No leaderboard results yet.