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/shinke-li/pointcvar

공식 코드

Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification

https://github.com/shuaizhao95/Unlearning

공식 코드

Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation

https://github.com/shuchiwu/eminspector

공식 코드

EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection

https://github.com/shymuel/diff-cleanse

공식 코드

Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models

https://github.com/sisl-uri/arch_backdoor_llm

공식 코드

Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor

https://github.com/sisl-uri/noiseattack

공식 코드

NoiseAttack: An Evasive Sample-Specific Multi-Targeted Backdoor Attack Through White Gaussian Noise

https://github.com/skoffas/going-in-style

공식 코드

Going In Style: Audio Backdoors Through Stylistic Transformations

https://github.com/slkdfjslkjfd/fl_fairness_attacks

공식 코드

Attacks on fairness in Federated Learning

https://github.com/spaxilia/recover-triggered-states

공식 코드

Recover Triggered States: Protect Model Against Backdoor Attack in Reinforcement Learning

https://github.com/sunh1113/efficient-backdoor-attacks-for-deep-neural-networks-in-real-world-scenarios

공식 코드

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

https://github.com/superrrpotato/Defending-Neural-Backdoors-via-Generative-Distribution-Modeling

공식 코드

Defending Neural Backdoors via Generative Distribution Modeling

https://github.com/thanhtrunghuynh93/fastfedul

공식 코드

Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience

https://github.com/thunlp/HiddenKiller

공식 코드

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger

https://github.com/thunlp/NeuBA

공식 코드

Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks

https://github.com/thunlp/ONION

공식 코드

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

https://github.com/thunlp/styleattack

공식 코드

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

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/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/ucsb-mlsec/troj_fm

공식 코드

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

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

공식 코드

Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks

https://github.com/usail-hkust/bkdfedgcn

공식 코드

Bkd-FedGNN: A Benchmark for Classification Backdoor Attacks on Federated Graph Neural Network

https://github.com/venomenhancer/venom

공식 코드

A general approach to enhance the survivability of backdoor attacks by decision path coupling

https://github.com/ventr1c/ugba

공식 코드

Unnoticeable Backdoor Attacks on Graph Neural Networks

https://github.com/wanghangpsu/mm-bd

공식 코드

MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic

https://github.com/wangren09/TrojanNetDetector

공식 코드

Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases

https://github.com/warisgill/FedDefender

공식 코드

FedDefender: Backdoor Attack Defense in Federated Learning

https://github.com/wecanshow/mcl

공식 코드

Model-Contrastive Learning for Backdoor Defense

https://github.com/xaiveryuan/patchbackdoor

공식 코드

PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification

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

공식 코드

BadCM: Invisible Backdoor Attack Against Cross-Modal Learning

https://github.com/xpf/Multi-Level-MMD-Regularization

공식 코드

Enhancing Backdoor Attacks with Multi-Level MMD Regularization

https://github.com/xtLyu/CrossBA

공식 코드

Cross-Context Backdoor Attacks against Graph Prompt Learning

https://github.com/xuefusiji/badrefsr

공식 코드

BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution

https://github.com/yinghuagao/siba

공식 코드

Backdoor Attack with Sparse and Invisible Trigger

https://github.com/yulongtzzz/Stealthy-Backdoors-as-Compression-Artifacts

공식 코드

Stealthy Backdoors as Compression Artifacts

https://github.com/yuweisunn/ADA

공식 코드

Semi-Targeted Model Poisoning Attack on Federated Learning via Backward Error Analysis

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