Papers with Code 아카이브
Adversarial Attack
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/20000yshust/swarm
공식 코드Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
https://github.com/2019chengong/offline_rl_poisoner
공식 코드BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
https://github.com/6tonystark6/scoreadv
공식 코드ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models
https://github.com/7777777cc/code
공식 코드BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning
https://github.com/ACM-MM-2020-Submission/Submission123
공식 코드https://github.com/AI-secure/T3
공식 코드T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack
https://github.com/AIM-Intelligence/SUDO
공식 코드https://github.com/APooladian/ProxLogBarrierAttack
공식 코드A principled approach for generating adversarial images under non-smooth dissimilarity metrics
https://github.com/ASU-ESIC-FAN-Lab/DEEPDUPA
공식 코드https://github.com/AaronSun2000/MakeupAttack
공식 코드MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup Transfer
https://github.com/Alan-Qin/Transfer_attack_RAP
공식 코드Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
https://github.com/AmirhoseinCh/DynamicPatch
공식 코드https://github.com/AnTao97/LGM
공식 코드Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network
https://github.com/AskExplain/synthetic_sampling
공식 코드https://github.com/AsrAttackSok/asr-attack-sok
공식 코드SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systems
https://github.com/Atipico1/robust-rag
공식 코드https://github.com/Bai-Li/STN-Code
공식 코드https://github.com/BaoWangMath/DNN-DataDependentActivation
공식 코드Adversarial Defense via Data Dependent Activation Function and Total Variation Minimization
https://github.com/BaoWangMath/EnResNet
공식 코드ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuracies
https://github.com/BardOfCodes/fda
공식 코드https://github.com/BillChan226/AgentPoison
공식 코드AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
https://github.com/BorealisAI/advertorch
공식 코드advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch
https://github.com/BravoLu/SSAE
공식 코드https://github.com/BreastGAN/experiment1
공식 코드https://github.com/BreastGAN/experiment2
공식 코드https://github.com/CAU-AutoML/Bitabuse
공식 코드BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks
https://github.com/CCCjiang/CTRL
공식 코드An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
https://github.com/CHENBIN99/AdaEA
공식 코드An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability
https://github.com/CHENGEZ/Attacking-by-Aligning
공식 코드Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection
https://github.com/CLIAgroup/ANDA
공식 코드Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
https://github.com/CMLI-NLP/HITL-GAT
공식 코드Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script
https://github.com/CVC-Lab/3D_ADV_Mesh_pytorch3d
공식 코드Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors
https://github.com/CZHQuality/AAA-Pix2pix
공식 코드A New Ensemble Adversarial Attack Powered by Long-term Gradient Memories
https://github.com/CatherineWong/dancin_seq2seq
공식 코드DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation
https://github.com/Chenfeng1271/L3A
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.