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 21–30 of 65 papers

TitleStatusHype
LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial AttacksCode0
DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local SmoothingCode0
PCLD: Point Cloud Layerwise Diffusion for Adversarial PurificationCode0
High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image SynthesisCode0
Carefully Blending Adversarial Training, Purification, and Aggregation Improves Adversarial RobustnessCode0
Language Guided Adversarial PurificationCode0
Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial AttacksCode0
Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs—0
Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification—0
Adversarial Text Purification: A Large Language Model Approach for Defense—0
Show:102550
← PrevPage 3 of 7Next →

No leaderboard results yet.