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 101–110 of 176 papers

TitleStatusHype
Quantifying (Hyper) Parameter Leakage in Machine Learning—0
QuantumLeak: Stealing Quantum Neural Networks from Cloud-based NISQ Machines—0
QUEEN: Query Unlearning against Model Extraction—0
Revealing Secrets From Pre-trained Models—0
SCME: A Self-Contrastive Method for Data-free and Query-Limited Model Extraction Attack—0
Security and Privacy Challenges in Deep Learning Models—0
Seeds Don't Lie: An Adaptive Watermarking Framework for Computer Vision Models—0
SEEK: model extraction attack against hybrid secure inference protocols—0
Split HE: Fast Secure Inference Combining Split Learning and Homomorphic Encryption—0
Stealing Deep Reinforcement Learning Models for Fun and Profit—0
Show:102550
← PrevPage 11 of 18Next →

Benchmark Results

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