Model extraction
55 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
Latest papers with no code
Better Decisions through the Right Causal World Model
Reinforcement learning (RL) agents have shown remarkable performances in various environments, where they can discover effective policies directly from sensory inputs.
CopyQNN: Quantum Neural Network Extraction Attack under Varying Quantum Noise
Quantum Neural Networks (QNNs) have shown significant value across domains, with well-trained QNNs representing critical intellectual property often deployed via cloud-based QNN-as-a-Service (QNNaaS) platforms.
ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction
Pre-trained models are valuable intellectual property, capturing both domain-specific and domain-invariant features within their weight spaces.
A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments
Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data.
Differentially private fine-tuned NF-Net to predict GI cancer type
Therefore, it is significant to classify a gastro-intestinal (GI) cancer tumor into MSI vs. MSS to provide appropriate treatment.
A Framework for Double-Blind Federated Adaptation of Foundation Models
However, the data that is required for this adaptation typically exists in silos across multiple entities (data owners) and cannot be collated at a central location due to regulations and privacy concerns.
Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI
Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity.
"FRAME: Forward Recursive Adaptive Model Extraction -- A Technique for Advance Feature Selection"
This study highlights the importance of assessing feature selection methods across varied datasets to ensure their robustness and generalizability.
HoneypotNet: Backdoor Attacks Against Model Extraction
In this work, we introduce a new defense paradigm called attack as defense which modifies the model's output to be poisonous such that any malicious users that attempt to use the output to train a substitute model will be poisoned.
Bounding-box Watermarking: Defense against Model Extraction Attacks on Object Detectors
Backdoor-based DNN watermarking is known as a promising defense against MEAs, wherein the defender injects a backdoor into extracted models via API responses.
