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/a1600012888/YOPO-You-Only-Propagate-Once

공식 코드

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle

https://github.com/a554b554/kWTA-Activation

공식 코드

Enhancing Adversarial Defense by k-Winners-Take-All

https://github.com/aamir-mustafa/pcl-adversarial-defense

공식 코드

Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks

https://github.com/aamir-mustafa/super-resolution-adversarial-defense

공식 코드

Image Super-Resolution as a Defense Against Adversarial Attacks

https://github.com/adverml/advopenood

공식 코드

Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors

https://github.com/adverml/multilid

공식 코드

Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection

https://github.com/alexklwong/stereopagnosia

공식 코드

Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations

https://github.com/alexklwong/targeted-adversarial-perturbations-monocular-depth

공식 코드

Targeted Adversarial Perturbations for Monocular Depth Prediction

https://github.com/alipay/A2-efficient-automated-attacker-for-boosting-adversarial-training

공식 코드

A2: Efficient Automated Attacker for Boosting Adversarial Training

https://github.com/amy-choi/AttackDefenseYOLO

공식 코드

Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarios

https://github.com/andiac/advpp

공식 코드

Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective

https://github.com/anirudh9784/Adversarial-Attacks-and-Defences

공식 코드

An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacks

https://github.com/anishathalye/obfuscated-gradients

공식 코드

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

https://github.com/araujoalexandre/lipschitz-sll-networks

공식 코드

A Unified Algebraic Perspective on Lipschitz Neural Networks

https://github.com/ashafahi/free_adv_train

공식 코드

Adversarial Training for Free!

https://github.com/aupendu/sr-uncertainty

공식 코드

Fast Bayesian Uncertainty Estimation and Reduction of Batch Normalized Single Image Super-Resolution Network

https://github.com/baogiadoan/IG-BNN

공식 코드

Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense

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

공식 코드

PCLD: Point Cloud Layerwise Diffusion for Adversarial Purification

https://github.com/c0510gy/AFLS-AED

공식 코드

A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detection

https://github.com/callous-youth/last

공식 코드

Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization

https://github.com/carlini/AmI

공식 코드

Is AmI (Attacks Meet Interpretability) Robust to Adversarial Examples?

https://github.com/cas-aisafetybasicresearchgroup/causaldiff

공식 코드

CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense

https://github.com/cassidylaidlaw/perceptual-advex

공식 코드

Perceptual Adversarial Robustness: Defense Against Unseen Threat Models

https://github.com/cc13qq/cad

공식 코드

Continual Adversarial Defense

https://github.com/centerforaisafety/adversarial-corruptions

공식 코드

Testing Robustness Against Unforeseen Adversaries

https://github.com/cfinlay/tulip

공식 코드

Scaleable input gradient regularization for adversarial robustness

https://github.com/changzhang777/ancra

공식 코드

Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria

https://github.com/chenboluo/adversarial-defense

공식 코드

Improving Adversarial Robustness via Decoupled Visual Representation Masking

https://github.com/chenhongge/RobustTrees

공식 코드

Robust Decision Trees Against Adversarial Examples

https://github.com/chihhuiho/disco

공식 코드

DISCO: Adversarial Defense with Local Implicit Functions

https://github.com/chs20/robustvlm

공식 코드

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

https://github.com/cihangxie/NIPS2017_adv_challenge_defense

공식 코드

Mitigating Adversarial Effects Through Randomization

https://github.com/cihangxie/SmoothAdversarialTraining

공식 코드

Smooth Adversarial Training

https://github.com/columbia/MTRobust

공식 코드

Multitask Learning Strengthens Adversarial Robustness

https://github.com/coperception/robosac

공식 코드

Among Us: Adversarially Robust Collaborative Perception by Consensus

https://github.com/cuge1995/IT-Defense

공식 코드

The art of defense: letting networks fool the attacker

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