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 11–20 of 65 papers

TitleStatusHype
FlowPure: Continuous Normalizing Flows for Adversarial PurificationCode1
Adversarial purification with Score-based generative modelsCode1
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial PurificationCode1
Adversarial Text Purification: A Large Language Model Approach for Defense—0
Adversarial Purification and Fine-tuning for Robust UDC Image Restoration—0
Adversarial Purification through Representation Disentanglement—0
Adversarially Robust Industrial Anomaly Detection Through Diffusion Model—0
ADBM: Adversarial diffusion bridge model for reliable adversarial purification—0
Adversarial Attacks and Robust Defenses in Speaker Embedding based Zero-Shot Text-to-Speech System—0
Adversarial purification for no-reference image-quality metrics: applicability study and new methods—0
Show:102550
← PrevPage 2 of 7Next →

No leaderboard results yet.