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/aryan-satpathy/backdoor

공식 코드

Towards Adversarial Robustness And Backdoor Mitigation in SSL

https://github.com/ase2023paper/fmt

공식 코드

Adversarial Feature Map Pruning for Backdoor

https://github.com/asif-hanif/baple

공식 코드

BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt Learning

https://github.com/bapfl/code

공식 코드

You Can Backdoor Personalized Federated Learning

https://github.com/bboylyg/abl

공식 코드

Anti-Backdoor Learning: Training Clean Models on Poisoned Data

https://github.com/bigml-cs-ucla/roclip

공식 코드

Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor Attacks

https://github.com/cgcl-codes/badhash

공식 코드

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label

https://github.com/charles-ydd/trojanrag

공식 코드

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

https://github.com/chasesecurity/spamdam

공식 코드

SpamDam: Towards Privacy-Preserving and Adversary-Resistant SMS Spam Detection

https://github.com/chichidd/backdoordynamicdnn

공식 코드

Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing

https://github.com/cristinalan/flowmur

공식 코드

FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge

https://github.com/damianliumin/non-adversarial_backdoor

공식 코드

Beating Backdoor Attack at Its Own Game

https://github.com/datasec-lab/codebreaker

공식 코드

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection

https://github.com/django-jiang/badchain

공식 코드

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

https://github.com/ekko-zn/ijcai2022-backdoor

공식 코드

Imperceptible Backdoor Attack: From Input Space to Feature Representation

https://github.com/ethz-spylab/rlhf-poisoning

공식 코드

Universal Jailbreak Backdoors from Poisoned Human Feedback

https://github.com/foreverzyh/defend_framework

공식 코드

BagFlip: A Certified Defense against Data Poisoning

https://github.com/ftrojanattack/ftrojan

공식 코드

Backdoor Attack through Frequency Domain

https://github.com/graph-axis/gcleaner

공식 코드

"No Matter What You Do": Purifying GNN Models via Backdoor Unlearning

https://github.com/grasses/poisonprompt

공식 코드

PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models

https://github.com/guowei-cn/cca_ud-universal-training-level-defence

공식 코드

Universal Detection of Backdoor Attacks via Density-based Clustering and Centroids Analysis

https://github.com/hanbocai/badspeech_soe

공식 코드

Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound

https://github.com/haowang-cqu/transtroj

공식 코드

Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability

https://github.com/havelhuang/EKiML-embed-knowledge-into-ML-model

공식 코드

Embedding and Extraction of Knowledge in Tree Ensemble Classifiers

https://github.com/hazardfy/fiba

공식 코드

FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis

https://github.com/hbrachemi/energy_backdoor

공식 코드

Energy Backdoor Attack to Deep Neural Networks

https://github.com/hku-tasr/anywheredoor

공식 코드

AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection

https://github.com/hong-xian/backdoor-attack

공식 코드

Generalization Bound and New Algorithm for Clean-Label Backdoor Attack

https://github.com/hsouri/Sleeper-Agent

공식 코드

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch

https://github.com/hsouri/gdp

공식 코드

Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion

https://github.com/huawei-lin/InplaceOnlineGBDT

공식 코드

Online Gradient Boosting Decision Tree: In-Place Updates for Efficient Adding/Deleting Data

https://github.com/huyvnphan/eccv2022-ribac

공식 코드

RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN

https://github.com/hxzhong1997/fsba

공식 코드

Few-Shot Backdoor Attacks on Visual Object Tracking

https://github.com/hychaochao/chat-models-backdoor-attacking

공식 코드

Exploring Backdoor Vulnerabilities of Chat Models

https://github.com/ibm/baddiffusion

공식 코드

How to Backdoor Diffusion Models?

https://github.com/ibm/villandiffusion

공식 코드

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models

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