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 21–30 of 176 papers

TitleStatusHype
Adversarial Exploitation of Policy Imitation—0
A Knowledge Representation Approach to Automated Mathematical Modelling—0
AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models—0
A Desynchronization-Based Countermeasure Against Side-Channel Analysis of Neural Networks—0
Automated Data-Driven Model Extraction and Validation of Inverter Dynamics with Grid Support Function—0
Automating Agential Reasoning: Proof-Calculi and Syntactic Decidability for STIT Logics—0
Bound Your Models! How to Make OWL an ASP Modeling Language—0
Beyond Labeling Oracles: What does it mean to steal ML models?—0
Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs—0
Business Process Text Sketch Automation Generation Using Large Language Model—0
Show:102550
← PrevPage 3 of 18Next →

Benchmark Results

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