High Accuracy and High Fidelity Extraction of Neural Networks

Research question

What are the limits of extracting neural networks from query access?

Key findings

Learning-based extraction produces high-accuracy copies; direct recovery gives functionally equivalent models for small networks - Formalises accuracy versus fidelity goals

Sources

arxiv.orghttps://arxiv.org/abs/1909.01838

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit research Report a correction or request removal

Related in Research Paper Library

Structured Decomposition for Reliable LLM-Generated Access Control Policies

This paper presents an LLM-based system that translates natural-language access control policies (NLACPs) into executable Rego code for Open Policy Agent (OPA). It provides a modular, end-to-end pipeline for policy…

Model extraction and stealing2026

Secrets That Survive Everything: Runtime Credential Exposure in Production Web Applications

Pre-deployment secret scanning operates only on source code, never on what a production application serves. We document two exploitation chains in which Azure AD client credentials and APIM subscription keys from…

Model extraction and stealing2026

End-to-End Hard-Label Cryptanalytic Model Extraction Using Efficient Sign Recovery

The importance of deep neural networks (DNNs) is widely recognized, and the parameters obtained through training are regarded as valuable assets. Recently, attacks that extract these parameters using only oracle…

Model extraction and stealing2026