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 141–150 of 176 papers

TitleStatusHype
BODAME: Bilevel Optimization for Defense Against Model Extraction—0
Model Extraction and Defenses on Generative Adversarial Networks—0
Grey-box Extraction of Natural Language Models—0
EXPLORING VULNERABILITIES OF BERT-BASED APIS—0
Sparsity-driven Digital Terrain Model Extraction—0
A Knowledge Representation Approach to Automated Mathematical Modelling—0
Monitoring-based Differential Privacy Mechanism Against Query-Flooding Parameter Duplication Attack—0
Leveraging Extracted Model Adversaries for Improved Black Box Attacks—0
Model Extraction Attacks on Graph Neural Networks: Taxonomy and RealizationCode0
Model extraction from counterfactual explanationsCode0
Show:102550
← PrevPage 15 of 18Next →

Benchmark Results

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