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
Entangled Threats: A Unified Kill Chain Model for Quantum Machine Learning Security—0
CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and AcquisitionCode0
Navigating the Deep: Signature Extraction on Deep Neural Networks—0
Explore the vulnerability of black-box models via diffusion models—0
GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors—0
MISLEADER: Defending against Model Extraction with Ensembles of Distilled ModelsCode0
Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning—0
On the interplay of Explainability, Privacy and Predictive Performance with Explanation-assisted Model Extraction—0
Better Decisions through the Right Causal World Model—0
CopyQNN: Quantum Neural Network Extraction Attack under Varying Quantum Noise—0
ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural NetworksCode1
ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction—0
A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environments—0
Differentially private fine-tuned NF-Net to predict GI cancer type—0
From Counterfactuals to Trees: Competitive Analysis of Model Extraction AttacksCode0
A Framework for Double-Blind Federated Adaptation of Foundation Models—0
Safety at Scale: A Comprehensive Survey of Large Model SafetyCode3
Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI—0
"FRAME: Forward Recursive Adaptive Model Extraction -- A Technique for Advance Feature Selection"—0
Neural Honeytrace: A Robust Plug-and-Play Watermarking Framework against Model Extraction AttacksCode1
HoneypotNet: Backdoor Attacks Against Model Extraction—0
Bounding-box Watermarking: Defense against Model Extraction Attacks on Object Detectors—0
Few-shot Model Extraction Attacks against Sequential Recommender Systems—0
A Hard-Label Cryptanalytic Extraction of Non-Fully Connected Deep Neural Networks using Side-Channel AttacksCode0
Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS WatermarkCode0
Show:102550
← PrevPage 1 of 8Next →

Benchmark Results

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