Papers with Code 아카이브

Adversarial Purification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

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

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/NVlabs/DiffPure

공식 코드

Diffusion Models for Adversarial Purification

https://github.com/NikolaiKyhne/Detecting-and-Defending-Against-Adversarial-Attacks

공식 코드

Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models

https://github.com/Visual-Conception-Group/LGAP

공식 코드

Language Guided Adversarial Purification

https://github.com/ZhangJC-2k/RandomSampling

공식 코드

Random Sampling for Diffusion-based Adversarial Purification

https://github.com/batuceng/diffusion-layer-robustness-pc

공식 코드

PCLD: Point Cloud Layerwise Diffusion for Adversarial Purification

https://github.com/cychomatica/audiopure

공식 코드

Defending against Adversarial Audio via Diffusion Model

https://github.com/deep-kaixun/videopure

공식 코드

VideoPure: Diffusion-based Adversarial Purification for Video Recognition

https://github.com/distrinet/flowpure

공식 코드

FlowPure: Continuous Normalizing Flows for Adversarial Purification

https://github.com/emaballarin/CARSO

공식 코드

Carefully Blending Adversarial Training, Purification, and Aggregation Improves Adversarial Robustness

https://github.com/ericyu97/uad-rs

공식 코드

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

https://github.com/fra31/auto-attack

공식 코드

ZeroPur: Succinct Training-Free Adversarial Purification

https://github.com/glin2022/atop

공식 코드

Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization

https://github.com/javyduck/diffsmooth

공식 코드

DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing

https://github.com/jinyiw/guideddiffusionpur

공식 코드

Guided Diffusion Model for Adversarial Purification

https://github.com/jmyoon1/adp

공식 코드

Adversarial purification with Score-based generative models

https://github.com/joana-cabral/lisard

공식 코드

LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks

https://github.com/kangmintong/diffattack

공식 코드

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification

https://github.com/mamerzouk/adversarial-purification

공식 코드

Diffusion-based Adversarial Purification for Intrusion Detection

https://github.com/ml-postech/robust-evaluation-of-diffusion-based-purification

공식 코드

Robust Evaluation of Diffusion-Based Adversarial Purification

https://github.com/msu-video-group/adversarial-defenses-for-iqa

공식 코드

Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics

https://github.com/mtailanian/diff-cf

공식 코드

Diffusion models meet image counter-forensics

https://github.com/mti-lab/HF-ADB

공식 코드

High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis

https://github.com/nowindbutrain/impure

공식 코드

Adversarial Purification of Information Masking

https://github.com/point0bar1/ebm-defense

공식 코드

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

https://github.com/serezd/gen_adversarial

공식 코드

Pre-trained Multiple Latent Variable Generative Models are good defenders against Adversarial Attacks

https://github.com/seu-proactivesecurity-group/malpurifier

공식 코드

MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks

https://github.com/tly18/tpap

공식 코드

Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM

https://github.com/adverML/GuidedDiffusionPur

Guided Diffusion Model for Adversarial Purification

https://github.com/zshsh98/eps-ad

Diffusion Models for Adversarial Purification

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.