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 121–130 of 176 papers

TitleStatusHype
Watermarking Graph Neural Networks based on Backdoor Attacks—0
Process Extraction from Text: Benchmarking the State of the Art and Paving the Way for Future ChallengesCode0
First to Possess His Statistics: Data-Free Model Extraction Attack on Tabular Data—0
HODA: Protecting DNNs Against Model Extraction Attacks via Hardness of Samples—0
NASPY: Automated Extraction of Automated Machine Learning Models—0
A Novel Watermarking Framework for Ownership Verification of DNN Architectures—0
Was my Model Stolen? Feature Sharing for Robust and Transferable Watermarks—0
Emerging AI Security Threats for Autonomous Cars -- Case Studies—0
Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs—0
Power-Based Attacks on Spatial DNN Accelerators—0
Show:102550
← PrevPage 13 of 18Next →

Benchmark Results

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