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 11–20 of 176 papers

TitleStatusHype
Neural Honeytrace: A Robust Plug-and-Play Watermarking Framework against Model Extraction AttacksCode1
Protecting Language Generation Models via Invisible WatermarkingCode1
"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced DistillationCode1
Entangled Watermarks as a Defense against Model ExtractionCode1
ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural NetworksCode1
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model ExtractionCode1
Black-Box Attacks on Sequential Recommenders via Data-Free Model ExtractionCode1
MEA-Defender: A Robust Watermark against Model Extraction AttackCode1
Efficient and Effective Model ExtractionCode0
VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional SpacesCode0
Show:102550
← PrevPage 2 of 18Next →

Benchmark Results

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