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/mist-project/mist

공식 코드

Mist: Towards Improved Adversarial Examples for Diffusion Models

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

공식 코드

Robust Evaluation of Diffusion-Based Adversarial Purification

https://github.com/mlmddetection/mlmddetection

공식 코드

Masked Language Model Based Textual Adversarial Example Detection

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/nengdong96/etndnet

공식 코드

Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification

https://github.com/nickeilf/diffusedef

공식 코드

DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising

https://github.com/nishiwen1214/dropattack

공식 코드

DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks

https://github.com/nisplab/at-bsl

공식 코드

Revisiting Adversarial Training under Long-Tailed Distributions

https://github.com/normaluhr/fast_bat

공식 코드

Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization

https://github.com/nowindbutrain/impure

공식 코드

Adversarial Purification of Information Masking

https://github.com/nsfzyzz/boundary_thickness

공식 코드

Boundary thickness and robustness in learning models

https://github.com/omnai-lab/robust-classifiers-under-the-lens-of-ebm

공식 코드

Shedding More Light on Robust Classifiers under the lens of Energy-based Models

https://github.com/optml-group/fast-bat

공식 코드

Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization

https://github.com/peck94/robust-width-defense

공식 코드

Robust width: A lightweight and certifiable adversarial defense

https://github.com/pgao-lab/DiffDf

공식 코드

Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking

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

공식 코드

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

https://github.com/point0bar1/ebm-life-cycle

공식 코드

EBM Life Cycle: MCMC Strategies for Synthesis, Defense, and Density Modeling

https://github.com/prinshul/prototype_neuralode_adv_attack

공식 코드

Adversarially Robust Prototypical Few-shot Segmentation with Neural-ODEs

https://github.com/psyonp/accidental_misalignment

공식 코드

Accidental Misalignment: Fine-Tuning Language Models Induces Unexpected Vulnerability

https://github.com/quinn777/cap

공식 코드

Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection

https://github.com/renmin1991/perturbation-inactivate

공식 코드

Perturbation Inactivation Based Adversarial Defense for Face Recognition

https://github.com/retis-ai/carla-gear

공식 코드

CARLA-GeAR: a Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Vision Models

https://github.com/rshaojimmy/ECCV2020-OSAD

공식 코드

Open-set Adversarial Defense

https://github.com/s-huu/TurningWeaknessIntoStrength

공식 코드

A New Defense Against Adversarial Images: Turning a Weakness into a Strength

https://github.com/salehsargolzaee/hopfield-integrated-test

공식 코드

Improving Out-of-Distribution Data Handling and Corruption Resistance via Modern Hopfield Networks

https://github.com/sennadir/noisygnn

공식 코드

A Simple and Yet Fairly Effective Defense for Graph Neural Networks

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/shaoyuanlo/artuda

공식 코드

Exploring Adversarially Robust Training for Unsupervised Domain Adaptation

https://github.com/shizhouxing/Fast-Certified-Robust-Training

공식 코드

Fast Certified Robust Training with Short Warmup

https://github.com/sjames40/adversarial-purification-for-mri

공식 코드

Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification

https://github.com/sjames40/smug_journal

공식 코드

Robust MRI Reconstruction by Smoothed Unrolling (SMUG)

https://github.com/softsys4ai/athena

공식 코드

ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense

https://github.com/sohaib730/argos-adversarial_detection

공식 코드

Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency

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