Hard-label cryptanalytic extraction of neural network models

DOI10.1007/978-981-96-0944-4_7MaRDI QIDQ6965156zbMATH OpenFDO

Authors Yi Chen, Xiaoyang Dong, Jian Guo, Yantian Shen, Anyu Wang, Xiaoyun Wang

Publication date 3 July 2025

Full work available at URL https://doi.org/10.1007/978-981-96-0944-4_7

zbMATH Keywords

cryptanalysisfunctionally equivalent extractionhard-labelReLu neural networks

Mathematics Subject Classification ID

Data encryption (aspects in computer science) (68P25) Artificial neural networks and deep learning (68T07) Cryptography (94A60)

Cites work

• Cryptanalytic extraction of neural network models
• Empirical Comparison of “Hard” and “Soft” Label Propagation for Relational Classification
• Machine learning: from theory to applications. Cooperative research at Siemens and MIT
• Polynomial time cryptanalytic extraction of neural network models
• Reconstructing a neural net from its output

Cited in

(3)

• Extracting some layers of deep neural networks in the hard-label setting
• Polynomial time cryptanalytic extraction of deep neural networks in the hard-label setting
• Navigating the deep: end-to-end extraction on deep neural networks

This page was built for publication: Hard-label cryptanalytic extraction of neural network models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6965156)