An Exact Poly-Time Membership-Queries Algorithm for Extraction a three-Layer ReLU Network

Built on

Robust and Resource-Efficient Identification of Two Hidden Layer Neural Networks
Original
Massimo Fornasier, Timo Klock, and Michael Rauchensteiner · 1907
Earlier work this paper cites.
High Accuracy and High Fidelity Extraction of Neural Networks
Original
Matthew Jagielski, Nicholas Carlini, David Berthelot, Alex Kurakin, and Nicolas Papernot · 1909
Earlier work this paper cites.
Reverse-engineering deep relu networks
Original
David Rolnick and Konrad P. Körding · 1910
Earlier work this paper cites.
The secret revealer: Generative model-inversion attacks against deep neural networks
Original
Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, and Dawn Song · 1911
Earlier work this paper cites.

Neural Network Learning: Theoretical Foundations
M. Anthony and P. Bartlet · 1999
Cited alongside, same era.
Cryptanalytic extraction of neural network models
Original
Nicholas Carlini, Matthew Jagielski, and Ilya Mironov · 2003
Cited alongside, same era.
benefits of depth in neural networks
Matus Telgarsky · 2016
Cited alongside, same era.
Stealing Machine Learning Models via Prediction APIs
Florian Tramer, Fan Zhang, Ari Juels, Michael K. Reiter, and Thomas Ristenpart · 2016
Cited alongside, same era.

How to steal a machine learning classifier with deep learning
Yi Shi, Yalin Sagduyu, and Alexander Grushin · 2017
Later among the works it cites.
Model Reconstruction from Model Explanations
Original
Smitha Milli, Ludwig Schmidt, Anca D. Dragan, and Moritz Hardt · 2019
Later among the works it cites.
Efficiently Learning Any One Hidden Layer ReLU Network From Queries
Sitan Chen, Adam R Klivans, and Raghu Meka · 2021
Closest in time.