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 76–100 of 176 papers

TitleStatusHype
FDINet: Protecting against DNN Model Extraction via Feature Distortion Index—0
Ownership Protection of Generative Adversarial Networks—0
NaturalFinger: Generating Natural Fingerprint with Generative Adversarial Networks—0
Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor WatermarkCode1
Model Extraction Attacks Against Reinforcement Learning Based Controllers—0
GrOVe: Ownership Verification of Graph Neural Networks using Embeddings—0
EZClone: Improving DNN Model Extraction Attack via Shape Distillation from GPU Execution Profiles—0
A Desynchronization-Based Countermeasure Against Side-Channel Analysis of Neural Networks—0
Model Extraction Attacks on Split Federated Learning—0
An anatomy-based V1 model: Extraction of Low-level Features, Reduction of distortion and a V1-inspired SOM—0
Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public DataCode0
A Survey on Event-based News Narrative Extraction—0
Protecting Language Generation Models via Invisible WatermarkingCode1
AUTOLYCUS: Exploiting Explainable AI (XAI) for Model Extraction Attacks against Interpretable Models—0
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model ExtractionCode1
Model Extraction Attack against Self-supervised Speech Models—0
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
Show:102550
← PrevPage 4 of 8Next →

Benchmark Results

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