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 26–50 of 65 papers

TitleStatusHype
Instant Adversarial Purification with Adversarial Consistency Distillation—0
Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds—0
Large Language Model Sentinel: LLM Agent for Adversarial Purification—0
Adversarial Purification for Data-Driven Power System Event Classifiers with Diffusion Models—0
LoRID: Low-Rank Iterative Diffusion for Adversarial Purification—0
MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model—0
Model-Free Adversarial Purification via Coarse-To-Fine Tensor Network Representation—0
MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification—0
Online Adversarial Purification based on Self-supervised Learning—0
Online Adversarial Purification based on Self-Supervision—0
Adversarial purification for no-reference image-quality metrics: applicability study and new methods—0
Adversarial Purification with the Manifold Hypothesis—0
PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks—0
Rapid Plug-in Defenders—0
Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness—0
Adversarial Purification through Representation Disentanglement—0
Text Adversarial Purification as Defense against Adversarial Attacks—0
Robust Diffusion Models for Adversarial Purification—0
Towards Adversarial Purification using Denoising AutoEncoders—0
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective—0
Towards more transferable adversarial attack in black-box manner—0
Adversarial Text Purification: A Large Language Model Approach for Defense—0
ADBM: Adversarial diffusion bridge model for reliable adversarial purification—0
Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information—0
Defending Against Frequency-Based Attacks with Diffusion Models—0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.