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 1–10 of 65 papers

TitleStatusHype
DiffCAP: Diffusion-based Cumulative Adversarial Purification for Vision Language Models—0
Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs—0
How Do Diffusion Models Improve Adversarial Robustness?—0
Towards more transferable adversarial attack in black-box manner—0
FlowPure: Continuous Normalizing Flows for Adversarial PurificationCode1
Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain—0
Defending Against Frequency-Based Attacks with Diffusion Models—0
LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial AttacksCode0
Model-Free Adversarial Purification via Coarse-To-Fine Tensor Network Representation—0
VideoPure: Diffusion-based Adversarial Purification for Video RecognitionCode0
Show:102550
← PrevPage 1 of 7Next →

No leaderboard results yet.