Papers with Code 아카이브

Adversarial Attack

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 4
평가표: 3
보존된 평가 기록: 9

An Adversarial Attack is a technique to find a perturbation that changes the prediction of a machine learning model. The perturbation can be very small and imperceptible to human eyes.

Source: Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

코드

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

https://github.com/tsingqguo/AttackTracker

SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking

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/uclaml/RayS

RayS: A Ray Searching Method for Hard-label Adversarial Attack

https://github.com/ucsb-nlp-chang/textgrad

Towards Deep Learning Models Resistant to Adversarial Attacks

https://github.com/ukky17/invert_MV_pytorch

Towards Evaluating the Robustness of Neural Networks

https://github.com/utsjiyaoli/qa-attack

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

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

Towards Deep Learning Models Resistant to Adversarial Attacks

https://github.com/verified-intelligence/alpha-beta-crown

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification

https://github.com/vijini/FM-GAN

Adversarial Text Generation via Feature-Mover's Distance

https://github.com/vincent861223/Train_BERT_With_TextFooler

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

https://github.com/vision-sjtu/rtaa

Robust Tracking against Adversarial Attacks

https://github.com/vladbataev/vib

Deep Variational Information Bottleneck

https://github.com/vtddggg/BilinearGAN_for_LBIE

Generative Adversarial Text to Image Synthesis

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

Provable defenses against adversarial examples via the convex outer adversarial polytope

https://github.com/wangyongjie-ntu/Learn-to-pay-attention

Learn To Pay Attention

https://github.com/wegodev2/virtual-prompt-injection

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection

https://github.com/windstormer/Cfd-CAM

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

https://github.com/wqj111186/TextFooler

Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

https://github.com/wu-haoze/Marabou

Efficient Neural Network Analysis with Sum-of-Infeasibilities

https://github.com/wubaoyuan/adversarial-attack-to-caption

Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables

https://github.com/wufanyou/EPGD

Efficient Project Gradient Descent for Ensemble Adversarial Attack

https://github.com/xandery-geek/BackdoorAttacks

A new Backdoor Attack in CNNs by training set corruption without label poisoning

https://github.com/xmc-aalto/adv-xmtc

BERT-ATTACK: Adversarial Attack Against BERT Using BERT

https://github.com/xqx12/daily-info

Neurotoxin: Durable Backdoors in Federated Learning

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

Certified Adversarial Robustness with Additive Noise

https://github.com/yangbo93/attack-method

Random Transformation of Image Brightness for Adversarial Attack

https://github.com/yanggeng1995/EATS

End-to-End Adversarial Text-to-Speech

https://github.com/yangyunfei16/DBIA

DBIA: Data-free Backdoor Injection Attack against Transformer Networks

https://github.com/yaoshiang/MobileNetV2-CIFAR-Cleverhans

On Detecting Adversarial Perturbations

https://github.com/yaq007/cleverhans

The Limitations of Deep Learning in Adversarial Settings

https://github.com/ydc123/Meta_Surrogate_Model

Training Meta-Surrogate Model for Transferable Adversarial Attack

https://github.com/yevgm/deepadv3d

Towards Evaluating the Robustness of Neural Networks

https://github.com/yiskw713/scorecam

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

https://github.com/yizhe-ang/detectron2-1

Adversarial Examples for Semantic Segmentation and Object Detection

https://github.com/yizhe-ang/fake-detection-lab

Adversarial Attack on Deep Learning-Based Splice Localization

https://github.com/ylhz/tf_to_pytorch_model

Patch-wise Attack for Fooling Deep Neural Network

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