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 41–50 of 65 papers

TitleStatusHype
Adversarial Purification of Information MaskingCode0
Diffusion models meet image counter-forensicsCode1
Adversarial Purification for Data-Driven Power System Event Classifiers with Diffusion Models—0
Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness—0
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial PurificationCode1
Diffusion-Based Adversarial Purification for Speaker Verification—0
Language Guided Adversarial PurificationCode0
Advancing Adversarial Robustness Through Adversarial Logit Update—0
DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local SmoothingCode0
Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion ModelsCode1
Show:102550
← PrevPage 5 of 7Next →

No leaderboard results yet.