Papers with Code 아카이브

Backdoor Attack

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 0
보존된 평가 기록: 0

Backdoor attacks inject maliciously constructed data into a training set so that, at test time, the trained model misclassifies inputs patched with a backdoor trigger as an adversarially-desired target class.

코드

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

https://github.com/20000yshust/swarm

공식 코드

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers

https://github.com/2019chengong/offline_rl_poisoner

공식 코드

BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets

https://github.com/7777777cc/code

공식 코드

BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning

https://github.com/AaronSun2000/MakeupAttack

공식 코드

MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup Transfer

https://github.com/BillChan226/AgentPoison

공식 코드

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

https://github.com/CCCjiang/CTRL

공식 코드

An Embarrassingly Simple Backdoor Attack on Self-supervised Learning

https://github.com/CHENGEZ/Attacking-by-Aligning

공식 코드

Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection

https://github.com/Chengxiao-Luo/Untargeted-Backdoor-Attack-against-Object-Detection

공식 코드

Untargeted Backdoor Attack against Object Detection

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/HarrialX/GraphBackdoor

공식 코드

https://github.com/HengerLi/RLBackdoorFL

공식 코드

Learning to Backdoor Federated Learning

https://github.com/KaiyuanZh/FLIP

공식 코드

FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning

https://github.com/KuofengGao/CIBA

공식 코드

Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning

https://github.com/KuofengGao/IRBA

공식 코드

Imperceptible and Robust Backdoor Attack in 3D Point Cloud

https://github.com/Lyz1213/BadEdit

공식 코드

BadEdit: Backdooring large language models by model editing

https://github.com/Megum1/DFST

공식 코드

Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification

https://github.com/SewoongLab/FLIP

공식 코드

Label Poisoning is All You Need

https://github.com/SewoongLab/ntk-backdoor

공식 코드

Few-shot Backdoor Attacks via Neural Tangent Kernels

https://github.com/ShannonAI/backdoor_nlg

공식 코드

Defending Against Backdoor Attacks in Natural Language Generation

https://github.com/ShihaoZhaoZSH/Video-Backdoor-Attack

공식 코드

Clean-Label Backdoor Attacks on Video Recognition Models

https://github.com/THUYimingLi/backdoor-learning-resources

공식 코드

Backdoor Learning: A Survey

https://github.com/TenneyHu/CrossLingualAttack

공식 코드

CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers

https://github.com/Tianyaz97/rf_backdoor

공식 코드

Protocol-agnostic and Data-free Backdoor Attacks on Pre-trained Models in RF Fingerprinting

https://github.com/TinfoilHat0/Defending-Against-Backdoors-with-Robust-Learning-Rate

공식 코드

Defending against Backdoors in Federated Learning with Robust Learning Rate

https://github.com/UMBCvision/Hidden-Trigger-Backdoor-Attacks

공식 코드

Hidden Trigger Backdoor Attacks

https://github.com/UMBCvision/SSL-Backdoor

공식 코드

Backdoor Attacks on Self-Supervised Learning

https://github.com/Vill-Lab/2023-TIFS-DTIBA

공식 코드

Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification

https://github.com/VinAIResearch/Warping-based_Backdoor_Attack-release

공식 코드

WaNet -- Imperceptible Warping-based Backdoor Attack

https://github.com/VinAIResearch/input-aware-backdoor-attack-release

공식 코드

Input-Aware Dynamic Backdoor Attack

https://github.com/aaaaaasuka/datafree_backdoor_attacks

공식 코드

Data Free Backdoor Attacks

https://github.com/agiresearch/asb

공식 코드

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

https://github.com/aiiu-lab/backdoorimageediting

공식 코드

Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking

https://github.com/alekseevskaia/orderbkd

공식 코드

OrderBkd: Textual backdoor attack through repositioning

https://github.com/alibaba/federatedscope

공식 코드

Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks

https://github.com/aliborji/Backdoor_defense

공식 코드

Adversarial examples are useful too!

https://github.com/arcelikacikkaynak/federated_learning

공식 코드

Anomaly Localization in Model Gradients Under Backdoor Attacks Against Federated Learning

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