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
Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language TasksCode0
FLuID: Mitigating Stragglers in Federated Learning using Invariant DropoutCode0
Stateful Detection of Model Extraction AttacksCode0
Protecting Intellectual Property of Language Generation APIs with Lexical WatermarkCode0
From Counterfactuals to Trees: Competitive Analysis of Model Extraction AttacksCode0
Model Extraction Attacks on Graph Neural Networks: Taxonomy and RealizationCode0
ACTIVETHIEF: Model Extraction Using Active Learning and Unannotated Public DataCode0
Watermarking Counterfactual ExplanationsCode0
Model extraction from counterfactual explanationsCode0
GUIDO: A Hybrid Approach to Guideline Discovery & Ordering from Natural Language TextsCode0
Show:102550
← PrevPage 15 of 18Next →

Benchmark Results

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