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 1–25 of 176 papers

TitleStatusHype
Safety at Scale: A Comprehensive Survey of Large Model SafetyCode3
Now You See Me (CME): Concept-based Model ExtractionCode1
MARLeME: A Multi-Agent Reinforcement Learning Model Extraction LibraryCode1
Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!Code1
FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model ExtractionCode1
Entangled Watermarks as a Defense against Model ExtractionCode1
MEME: Generating RNN Model Explanations via Model ExtractionCode1
MEME: Generating RNN Model Explanations via Model ExtractionCode1
Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor WatermarkCode1
Protecting Language Generation Models via Invisible WatermarkingCode1
Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a ServiceCode1
ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural NetworksCode1
"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced DistillationCode1
Neural Honeytrace: A Robust Plug-and-Play Watermarking Framework against Model Extraction AttacksCode1
Black-Box Attacks on Sequential Recommenders via Data-Free Model ExtractionCode1
Data-Free Model ExtractionCode1
Cryptanalytic Extraction of Neural Network ModelsCode1
MEA-Defender: A Robust Watermark against Model Extraction AttackCode1
From Counterfactuals to Trees: Competitive Analysis of Model Extraction AttacksCode0
GUIDO: A Hybrid Approach to Guideline Discovery & Ordering from Natural Language TextsCode0
VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional SpacesCode0
A Hard-Label Cryptanalytic Extraction of Non-Fully Connected Deep Neural Networks using Side-Channel AttacksCode0
FLuID: Mitigating Stragglers in Federated Learning using Invariant DropoutCode0
Knowledge Distillation-Based Model Extraction Attack using GAN-based Private Counterfactual ExplanationsCode0
Defense Against Model Extraction Attacks on Recommender SystemsCode0
Show:102550
← PrevPage 1 of 8Next →

Benchmark Results

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