Adversarial Purification

17 papers with code • 0 benchmarks • 0 datasets

A class of adversarial defense methods that remove adversarial perturbations using a generative model.

Most implemented papers

Diffusion Models for Adversarial Purification

NVlabs/DiffPure 16 May 2022

Adversarial purification refers to a class of defense methods that remove adversarial perturbations using a generative model.

Guided Diffusion Model for Adversarial Purification

jinyiw/guideddiffusionpur 30 May 2022

In this paper, we propose a novel purification approach, referred to as guided diffusion model for purification (GDMP), to help protect classifiers from adversarial attacks.

Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models

point0bar1/ebm-defense ICLR 2021

Our contributions are 1) an improved method for training EBM's with realistic long-run MCMC samples, 2) an Expectation-Over-Transformation (EOT) defense that resolves theoretical ambiguities for stochastic defenses and from which the EOT attack naturally follows, and 3) state-of-the-art adversarial defense for naturally-trained classifiers and competitive defense compared to adversarially-trained classifiers on Cifar-10, SVHN, and Cifar-100.

Adversarial purification with Score-based generative models

jmyoon1/adp 11 Jun 2021

Recently, an Energy-Based Model (EBM) trained with Markov-Chain Monte-Carlo (MCMC) has been highlighted as a purification model, where an attacked image is purified by running a long Markov-chain using the gradients of the EBM.

Defending against Adversarial Audio via Diffusion Model

cychomatica/audiopure 2 Mar 2023

In this paper, we propose an adversarial purification-based defense pipeline, AudioPure, for acoustic systems via off-the-shelf diffusion models.

Robust Evaluation of Diffusion-Based Adversarial Purification

ml-postech/robust-evaluation-of-diffusion-based-purification ICCV 2023

We analyze the current practices and provide a new guideline for measuring the robustness of purification methods against adversarial attacks.

Carefully Blending Adversarial Training and Purification Improves Adversarial Robustness

emaballarin/CARSO 25 May 2023

In this work, we propose a novel adversarial defence mechanism for image classification - CARSO - blending the paradigms of adversarial training and adversarial purification in a synergistic robustness-enhancing way.

Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Models

ericyu97/uad-rs 31 Jul 2023

Deep neural networks (DNNs) have risen to prominence as key solutions in numerous AI applications for earth observation (AI4EO).

DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing

javyduck/diffsmooth 28 Aug 2023

Diffusion models have been leveraged to perform adversarial purification and thus provide both empirical and certified robustness for a standard model.

Language Guided Adversarial Purification

Visual-Conception-Group/LGAP 19 Sep 2023

Adversarial purification using generative models demonstrates strong adversarial defense performance.