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 1–10 of 176 papers

TitleStatusHype
Safety at Scale: A Comprehensive Survey of Large Model SafetyCode3
ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural NetworksCode1
Neural Honeytrace: A Robust Plug-and-Play Watermarking Framework against Model Extraction AttacksCode1
"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced DistillationCode1
MEA-Defender: A Robust Watermark against Model Extraction AttackCode1
Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a ServiceCode1
Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor WatermarkCode1
Protecting Language Generation Models via Invisible WatermarkingCode1
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model ExtractionCode1
Black-Box Attacks on Sequential Recommenders via Data-Free Model ExtractionCode1
Show:102550
← PrevPage 1 of 18Next →

Benchmark Results

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