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
LoRID: Low-Rank Iterative Diffusion for Adversarial Purification—0
MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model—0
Diffusion-based Adversarial Purification for Intrusion DetectionCode0
Random Sampling for Diffusion-based Adversarial PurificationCode0
High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image SynthesisCode0
VideoPure: Diffusion-based Adversarial Purification for Video RecognitionCode0
Adversarial Purification of Information MaskingCode0
PCLD: Point Cloud Layerwise Diffusion for Adversarial PurificationCode0
Language Guided Adversarial PurificationCode0
Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial AttacksCode0
LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial AttacksCode0
Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion ModelsCode0
DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local SmoothingCode0
Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSMCode0
Carefully Blending Adversarial Training, Purification, and Aggregation Improves Adversarial RobustnessCode0
Show:102550
← PrevPage 2 of 2Next →

No leaderboard results yet.