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 61–70 of 176 papers

TitleStatusHype
An anatomy-based V1 model: Extraction of Low-level Features, Reduction of distortion and a V1-inspired SOM—0
Enhancing TinyML Security: Study of Adversarial Attack Transferability—0
Emerging AI Security Threats for Autonomous Cars -- Case Studies—0
Beyond Labeling Oracles: What does it mean to steal ML models?—0
Efficient Model Extraction via Boundary Sampling—0
Efficiently Learning One Hidden Layer ReLU Networks From Queries—0
Better Decisions through the Right Causal World Model—0
Adversarial Exploitation of Policy Imitation—0
Efficiently Learning Any One Hidden Layer ReLU Network From Queries—0
Automating Agential Reasoning: Proof-Calculi and Syntactic Decidability for STIT Logics—0
Show:102550
← PrevPage 7 of 18Next →

Benchmark Results

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