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 51–65 of 65 papers

TitleStatusHype
Rapid Plug-in Defenders—0
Carefully Blending Adversarial Training, Purification, and Aggregation Improves Adversarial RobustnessCode0
Robust Evaluation of Diffusion-Based Adversarial PurificationCode1
Defending against Adversarial Audio via Diffusion ModelCode1
Adversarial Purification with the Manifold Hypothesis—0
Towards Adversarial Purification using Denoising AutoEncoders—0
Guided Diffusion Model for Adversarial Purification from Random Noise—0
Guided Diffusion Model for Adversarial PurificationCode1
Diffusion Models for Adversarial PurificationCode2
Text Adversarial Purification as Defense against Adversarial Attacks—0
Adversarial Purification through Representation Disentanglement—0
Adversarial purification with Score-based generative modelsCode1
Online Adversarial Purification based on Self-Supervision—0
Online Adversarial Purification based on Self-supervised Learning—0
Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based ModelsCode1
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.