Papers with Code 아카이브

Adversarial Defense

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

2

평가표

10

보존된 평가 기록

28

코드

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

https://github.com/tcwangshiqi-columbia/ReluVal

Efficient Formal Safety Analysis of Neural Networks

https://github.com/thomashopkins32/PGDAdversarialLearning

Towards Deep Learning Models Resistant to Adversarial Attacks

https://github.com/tianzheng4/Distributionally-Adversarial-Attack

Towards Deep Learning Models Resistant to Adversarial Attacks

https://github.com/tuscan-chicken-wrap/ECE260FinalProject

ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models

https://github.com/val-iisc/flss

Towards Deep Learning Models Resistant to Adversarial Attacks

https://github.com/vtjeng/MIPVerify.jl

Certified Defenses against Adversarial Examples

https://github.com/xilaili/AOGNet

AOGNets: Compositional Grammatical Architectures for Deep Learning

https://github.com/xinli0928/Defending

Defending against adversarial attacks on medical imaging AI system, classification or detection?

https://github.com/xzh0u/randomized-smoothing

Certified Adversarial Robustness via Randomized Smoothing

https://github.com/yaodongyu/projnorm

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

https://github.com/yaq007/cleverhans

The Limitations of Deep Learning in Adversarial Settings

https://github.com/yueatsprograms/ttt_cifar_release

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

https://github.com/yueatsprograms/ttt_imagenet_release

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

https://github.com/zibojia/rslad

Towards Deep Learning Models Resistant to Adversarial Attacks

https://github.com/zijianh4/CROP-leaderboard.github.io

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

https://github.com/zjfheart/Friendly-Adversarial-Training

Towards Deep Learning Models Resistant to Adversarial Attacks

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

Diffusion Models for Adversarial Purification

https://github.com/zudi-lin/RIDE

White-Box Adversarial Defense via Self-Supervised Data Estimation

https://gitlab.com/secml/secml

Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

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