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 31–40 of 176 papers

TitleStatusHype
MeaeQ: Mount Model Extraction Attacks with Efficient QueriesCode0
From Counterfactuals to Trees: Competitive Analysis of Model Extraction AttacksCode0
Robust and Minimally Invasive Watermarking for EaaSCode0
DAWN: Dynamic Adversarial Watermarking of Neural NetworksCode0
GUIDO: A Hybrid Approach to Guideline Discovery & Ordering from Natural Language TextsCode0
Defense Against Model Extraction Attacks on Recommender SystemsCode0
CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and AcquisitionCode0
FLuID: Mitigating Stragglers in Federated Learning using Invariant DropoutCode0
Deep Neural Network Fingerprinting by Conferrable Adversarial ExamplesCode0
Efficient and Effective Model ExtractionCode0
Show:102550
← PrevPage 4 of 18Next →

Benchmark Results

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