Papers with Code 아카이브

Model extraction

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 1
보존된 평가 기록: 1

Model extraction attacks, aka model stealing attacks, are used to extract the parameters from the target model. Ideally, the adversary will be able to steal and replicate a model that will have a very similar performance to the target model.

코드

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

https://github.com/BirkhoffG/CFMark

공식 코드

Watermarking Counterfactual Explanations

https://github.com/FatimaEzzedinee/Knowledge-Distillation-Based-Model-Extraction-Attack-using-GAN-based-Private-CFs

공식 코드

Knowledge Distillation-Based Model Extraction Attack using GAN-based Private Counterfactual Explanations

https://github.com/GradOpt/E3

공식 코드

Efficient and Effective Model Extraction

https://github.com/LabRAI/ATOM

공식 코드

ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks

https://github.com/Pter61/vlpmarker

공식 코드

Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service

https://github.com/TrustworthyGNN/MEA-GNN

공식 코드

Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization

https://github.com/XsongyangX/uml-translation-3step

공식 코드

Towards Automatically Extracting UML Class Diagrams from Natural Language Specifications

https://github.com/aiot-mlsys-lab/fedrolex

공식 코드

FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction

https://github.com/aivodji/mrce

공식 코드

Model extraction from counterfactual explanations

https://github.com/akshitjindal1/aot_wacv

공식 코드

Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selection

https://github.com/anudeex/warden

공식 코드

WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection

https://github.com/c-w-d/meaeq

공식 코드

MeaeQ: Mount Model Extraction Attacks with Efficient Queries

https://github.com/cake-lab/datafree-model-extraction

공식 코드

Data-Free Model Extraction

https://github.com/cleverhans-lab/entangled-watermark

공식 코드

Entangled Watermarks as a Defense against Model Extraction

https://github.com/cleverhans-lab/ssl-attacks-defenses

공식 코드

On the Difficulty of Defending Self-Supervised Learning against Model Extraction

https://github.com/debabrota-basu/marich

공식 코드

Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data

https://github.com/dmitrykazhdan/CME

공식 코드

Now You See Me (CME): Concept-based Model Extraction

https://github.com/dmitrykazhdan/MARLeME

공식 코드

MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library

https://github.com/dmitrykazhdan/MEME-RNN-XAI

공식 코드

MEME: Generating RNN Model Explanations via Model Extraction

https://github.com/ftramer/Steal-ML

공식 코드

Stealing Machine Learning Models via Prediction APIs

https://github.com/google-research/cryptanalytic-model-extraction

공식 코드

Cryptanalytic Extraction of Neural Network Models

https://github.com/google-research/language/tree/master/language/bert_extraction

공식 코드

Thieves on Sesame Street! Model Extraction of BERT-based APIs

https://github.com/hannafoe/cryptanalytical-extraction

공식 코드

Beyond Slow Signs in High-fidelity Model Extraction

https://github.com/illidanlab/single_oodwatermark

공식 코드

Safe and Robust Watermark Injection with a Single OoD Image

https://github.com/iwang05/fluid

공식 코드

FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropout

https://github.com/labrai/cega

공식 코드

CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition

https://github.com/labrai/misleader

공식 코드

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

https://github.com/liangzid/alignmentextraction

공식 코드

"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation

https://github.com/liangzid/lord-mea

공식 코드

"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation

https://github.com/liudan193/ESpeW

공식 코드

Robust and Minimally Invasive Watermarking for EaaS

https://github.com/liyuxuan-github/mat

공식 코드

Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data

https://github.com/lvpeizhuo/mea-defender

공식 코드

MEA-Defender: A Robust Watermark against Model Extraction Attack

https://github.com/msu-mlsys-lab/fedrolex

공식 코드

FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction

https://github.com/neurht/neurht

공식 코드

Neural Honeytrace: A Robust Plug-and-Play Watermarking Framework against Model Extraction Attacks

https://github.com/nils-freyer/guido

공식 코드

GUIDO: A Hybrid Approach to Guideline Discovery & Ordering from Natural Language Texts

https://github.com/pasandissanayake/model-reconstruction-using-counterfactuals

공식 코드

Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory

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