Model extraction
40 papers with code • 1 benchmarks • 2 datasets
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.
Benchmarks
These leaderboards are used to track progress in Model extraction
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Libraries
Use these libraries to find Model extraction models and implementations
Data Collected with Package Delivery Quadcopter Drone
UML Classes With Specs
Most implemented papers
ACTIVETHIEF: Model Extraction Using Active Learning and Unannotated Public Data
We demonstrate that (1) it is possible to use ACTIVETHIEF to extract deep classifiers trained on a variety of datasets from image and text domains, while querying the model with as few as 10-30% of samples from public datasets, (2) the resulting model exhibits a higher transferability success rate of adversarial examples than prior work, and (3) the attack evades detection by the state-of-the-art model extraction detection method, PRADA.
Cryptanalytic Extraction of Neural Network Models
google-research/cryptanalytic-model-extraction
•
•
We argue that the machine learning problem of model extraction is actually a cryptanalytic problem in disguise, and should be studied as such.
MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library
Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields.
Model extraction from counterfactual explanations
aivodji/mrce
•
•
Post-hoc explanation techniques refer to a posteriori methods that can be used to explain how black-box machine learning models produce their outcomes.
MEME: Generating RNN Model Explanations via Model Extraction
dmitrykazhdan/MEME-RNN-XAI
•
•
NeurIPS Workshop HAMLETS 2020
Recurrent Neural Networks (RNNs) have achieved remarkable performance on a range of tasks.
Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization
Machine learning models are shown to face a severe threat from Model Extraction Attacks, where a well-trained private model owned by a service provider can be stolen by an attacker pretending as a client.
Now You See Me (CME): Concept-based Model Extraction
Deep Neural Networks (DNNs) have achieved remarkable performance on a range of tasks.
MEME: Generating RNN Model Explanations via Model Extraction
dmitrykazhdan/MEME-RNN-XAI
•
•
Recurrent Neural Networks (RNNs) have achieved remarkable performance on a range of tasks.
Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!
xlhex/extract_and_transfer
•
•
NAACL 2021
Finally, we investigate two defence strategies to protect the victim model and find that unless the performance of the victim model is sacrificed, both model ex-traction and adversarial transferability can effectively compromise the target models
Stateful Detection of Model Extraction Attacks
Machine-Learning-as-a-Service providers expose machine learning (ML) models through application programming interfaces (APIs) to developers.
