Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Yi, Dong, Xiaoyang, Ma, Ruijie, Shen, Yantian, Wang, Anyu, Yu, Hongbo, Wang, Xiaoyun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.16620
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908549297209344
author Chen, Yi
Dong, Xiaoyang
Ma, Ruijie
Shen, Yantian
Wang, Anyu
Yu, Hongbo
Wang, Xiaoyun
author_facet Chen, Yi
Dong, Xiaoyang
Ma, Ruijie
Shen, Yantian
Wang, Anyu
Yu, Hongbo
Wang, Xiaoyun
contents The machine learning problem of model extraction was first introduced in 1991 and gained prominence as a cryptanalytic challenge starting with Crypto 2020. For over three decades, research in this field has primarily focused on ReLU-based neural networks. In this work, we take the first step towards the cryptanalytic extraction of PReLU neural networks, which employ more complex nonlinear activation functions than their ReLU counterparts. We propose a raw output-based parameter recovery attack for PReLU networks and extend it to more restrictive scenarios where only the top-m probability scores are accessible. Our attacks are rigorously evaluated through end-to-end experiments on diverse PReLU neural networks, including models trained on the MNIST dataset. To the best of our knowledge, this is the first practical demonstration of PReLU neural network extraction across three distinct attack scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Delving into Cryptanalytic Extraction of PReLU Neural Networks
Chen, Yi
Dong, Xiaoyang
Ma, Ruijie
Shen, Yantian
Wang, Anyu
Yu, Hongbo
Wang, Xiaoyun
Cryptography and Security
The machine learning problem of model extraction was first introduced in 1991 and gained prominence as a cryptanalytic challenge starting with Crypto 2020. For over three decades, research in this field has primarily focused on ReLU-based neural networks. In this work, we take the first step towards the cryptanalytic extraction of PReLU neural networks, which employ more complex nonlinear activation functions than their ReLU counterparts. We propose a raw output-based parameter recovery attack for PReLU networks and extend it to more restrictive scenarios where only the top-m probability scores are accessible. Our attacks are rigorously evaluated through end-to-end experiments on diverse PReLU neural networks, including models trained on the MNIST dataset. To the best of our knowledge, this is the first practical demonstration of PReLU neural network extraction across three distinct attack scenarios.
title Delving into Cryptanalytic Extraction of PReLU Neural Networks
topic Cryptography and Security
url https://arxiv.org/abs/2509.16620