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/thunlp/ONION

공식 코드

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

https://github.com/thunlp/OpenAttack

공식 코드

OpenAttack: An Open-source Textual Adversarial Attack Toolkit

https://github.com/thunlp/SememePSO-Attack

공식 코드

Word-level Textual Adversarial Attacking as Combinatorial Optimization

https://github.com/thunlp/SememeRNN

공식 코드

Improving Sequence Modeling Ability of Recurrent Neural Networks via Sememes

https://github.com/thunlp/robtest

공식 코드

From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework

https://github.com/thunlp/styleattack

공식 코드

Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer

https://github.com/thuwzy/Cluster-Attack

공식 코드

Cluster Attack: Query-based Adversarial Attacks on Graphs with Graph-Dependent Priors

https://github.com/thuydung-icthust/FedGrad_Backdoor_Attack

공식 코드

FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection

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

공식 코드

Distributionally Adversarial Attack

https://github.com/tly18/tpap

공식 코드

Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM

https://github.com/tokaka22/gmaa

공식 코드

Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition

https://github.com/tomvii/adv_mia

공식 코드

Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges

https://github.com/torrvision/whoneedsadversaries

공식 코드

With Friends Like These, Who Needs Adversaries?

https://github.com/trais-lab/adversarial-attack-data-attribution

공식 코드

Adversarial Attacks on Data Attribution

https://github.com/treelli/apt

공식 코드

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models

https://github.com/treelli/combating-ro-advlc

공식 코드

Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and Regularization

https://github.com/treelli/instance-adaptive-smoothness-enhanced-at

공식 코드

Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothing

https://github.com/tristachi/ensemblekw

공식 코드

On the Perils of Cascading Robust Classifiers

https://github.com/trlou/hit-adv

공식 코드

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds

https://github.com/trustai/deepsava

공식 코드

Sparse Adversarial Video Attacks with Spatial Transformations

https://github.com/trustairlab/hatebench

공식 코드

HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns

https://github.com/tsachiblau/Class-Conditioned-Transformation-for-Enhanced-Robust-Image-Classification

공식 코드

Class-Conditioned Transformation for Enhanced Robust Image Classification

https://github.com/tsbiosky/PointACL

공식 코드

PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack

https://github.com/tsingqguo/ABBA

공식 코드

Watch out! Motion is Blurring the Vision of Your Deep Neural Networks

https://github.com/tsingqguo/jadena

공식 코드

Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection

https://github.com/tudelft-cda-lab/GROOT

공식 코드

Efficient Training of Robust Decision Trees Against Adversarial Examples

https://github.com/tuomaso/radial_rl

공식 코드

Robust Deep Reinforcement Learning through Adversarial Loss

https://github.com/tuomaso/radial_rl_v2

공식 코드

Robust Deep Reinforcement Learning through Adversarial Loss

https://github.com/tzvilederer/silent-killer

공식 코드

Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack

https://github.com/ubc-tea/backdoor_multimodal_foundation_model

공식 코드

Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP

https://github.com/uclaml/Frank-Wolfe-AdvML

공식 코드

A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks

https://github.com/ucsb-mlsec/troj_fm

공식 코드

TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models

https://github.com/ukp-square/square-core

공식 코드

UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA

https://github.com/ulab-uiuc/safescientist

공식 코드

SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents

https://github.com/umd-huang-lab/protected

공식 코드

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

https://github.com/unispac/subnet-replacement-attack

공식 코드

Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks

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