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 101–125 of 176 papers

TitleStatusHype
Seeds Don't Lie: An Adaptive Watermarking Framework for Computer Vision Models—0
A Practical Introduction to Side-Channel Extraction of Deep Neural Network Parameters—0
Towards Automatically Extracting UML Class Diagrams from Natural Language SpecificationsCode0
SEEK: model extraction attack against hybrid secure inference protocols—0
DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking—0
Revealing Secrets From Pre-trained Models—0
EVE: Environmental Adaptive Neural Network Models for Low-power Energy Harvesting System—0
On the amplification of security and privacy risks by post-hoc explanations in machine learning models—0
A Framework for Understanding Model Extraction Attack and Defense—0
On the Difficulty of Defending Self-Supervised Learning against Model ExtractionCode0
DualCF: Efficient Model Extraction Attack from Counterfactual Explanations—0
Stealing and Evading Malware Classifiers and Antivirus at Low False Positive ConditionsCode0
Split HE: Fast Secure Inference Combining Split Learning and Homomorphic Encryption—0
On the Effectiveness of Dataset Watermarking in Adversarial SettingsCode0
Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations—0
Increasing the Cost of Model Extraction with Calibrated Proof of Work—0
Protecting Intellectual Property of Language Generation APIs with Lexical WatermarkCode0
Efficiently Learning One Hidden Layer ReLU Networks From Queries—0
Efficiently Learning Any One Hidden Layer ReLU Network From Queries—0
DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories—0
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
Show:102550
← PrevPage 5 of 8Next →

Benchmark Results

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