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/Chengxiao-Luo/Untargeted-Backdoor-Attack-against-Object-Detection

공식 코드

Untargeted Backdoor Attack against Object Detection

https://github.com/Cold-Winter/Nattack

공식 코드

NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks

https://github.com/DAI-Lab/fibber

공식 코드

R&R: Metric-guided Adversarial Sentence Generation

https://github.com/DSE-MSU/DeepRobust

공식 코드

Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies

https://github.com/EdisonLeeeee/SGAttack

공식 코드

Adversarial Attack on Large Scale Graph

https://github.com/Equationliu/GA-Attack

공식 코드

Towards Transferable Unrestricted Adversarial Examples with Minimum Changes

https://github.com/EricDai0/3DASC

공식 코드

Transferable 3D Adversarial Shape Completion using Diffusion Models

https://github.com/EricDai0/AdvGCGAN

공식 코드

Generating Unrestricted 3D Adversarial Point Clouds

https://github.com/EricDai0/advdiff

공식 코드

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models

https://github.com/EthanChu7/CADE

공식 코드

Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples

https://github.com/ExplorerFreda/VSE-C

공식 코드

Learning Visually-Grounded Semantics from Contrastive Adversarial Samples

https://github.com/FenHua/DetDak

공식 코드

Object Hider: Adversarial Patch Attack Against Object Detectors

https://github.com/FireBERT-author/FireBERT

공식 코드

FireBERT: Hardening BERT-based classifiers against adversarial attack

https://github.com/FlaAI/TSFool-adversarial-time-series-generation-to-fool-RNNs

공식 코드

TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack

https://github.com/FrankShi9/Attention-Mask-Attack

공식 코드

Attention Masks Help Adversarial Attacks to Bypass Safety Detectors

https://github.com/Fraunhofer-AISEC/towards-resistant-audio-adversarial-examples

공식 코드

Towards Resistant Audio Adversarial Examples

https://github.com/Fraunhofer-AISEC/towards_resistant_audio_adversarial_examples

공식 코드

Towards Resistant Audio Adversarial Examples

https://github.com/FrostbiteXSW/SCAE_Attack

공식 코드

An Evasion Attack against Stacked Capsule Autoencoder

https://github.com/FrostbiteXSW/SCAE_L2_Attack

공식 코드

An Evasion Attack against Stacked Capsule Autoencoder

https://github.com/FuChong-cyber/Data-Free-Neural-Backdoor-Detector-FreeEagle

공식 코드

FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases

https://github.com/Gerda92/adversarial_transfer_factors

공식 코드

Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors

https://github.com/GianlucaMaragliano/Adversarial_RL_XSS

공식 코드

XSS Adversarial Attacks Based on Deep Reinforcement Learning: A Replication and Extension Study

https://github.com/Hadisalman/smoothing-adversarial

공식 코드

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

https://github.com/HaimFisher/fingerprints-armor

공식 코드

Neural Fingerprints for Adversarial Attack Detection

https://github.com/HanshuYAN/TisODE

공식 코드

On Robustness of Neural Ordinary Differential Equations

https://github.com/HaohanWang/HFC

공식 코드

High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

https://github.com/HarrialX/GraphBackdoor

공식 코드

https://github.com/HengerLi/RLBackdoorFL

공식 코드

Learning to Backdoor Federated Learning

https://github.com/IBM/composite-adv

공식 코드

CARBEN: Composite Adversarial Robustness Benchmark

https://github.com/ICT-MIRACLE-lab/Hierarchical_Feature_Constraint

공식 코드

A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks

https://github.com/IdoGalil/ACE

공식 코드

Disrupting Deep Uncertainty Estimation Without Harming Accuracy

https://github.com/JHL-HUST/ATDA

공식 코드

Improving the Generalization of Adversarial Training with Domain Adaptation

https://github.com/JHL-HUST/FGPM

공식 코드

Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text Attacks

https://github.com/JHL-HUST/SI-NI-FGSM

공식 코드

Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks

https://github.com/JensBayer/transferability

공식 코드

Network transferability of adversarial patches in real-time object detection

https://github.com/JetRichardLee/Attack-XGNN

공식 코드

Graph Neural Network Explanations are Fragile

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