SOTAVerified

Model extraction

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 71–80 of 176 papers

TitleStatusHype
DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking—0
DualCF: Efficient Model Extraction Attack from Counterfactual Explanations—0
Automated Data-Driven Model Extraction and Validation of Inverter Dynamics with Grid Support Function—0
Don't encrypt the data; just approximate the model \ Towards Secure Transaction and Fair Pricing of Training Data—0
Differentially private fine-tuned NF-Net to predict GI cancer type—0
Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training—0
AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models—0
A Knowledge Representation Approach to Automated Mathematical Modelling—0
A Desynchronization-Based Countermeasure Against Side-Channel Analysis of Neural Networks—0
Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training—0
Show:102550
← PrevPage 8 of 18Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1three-step-originalExact Match0.17—Unverified