First Verification of Rogue ONU Recognition in Commercial GPON System Based on Machine Learning

We first demonstrate rogue ONU identification in commercial GPON system with waveform feature extraction. The experimental results show that the average identification accuracy can reach 90.69%/92.95%/96.57%/99.37% within 32 ONUs for Random Forest/KNN/CNN/ResNet, respectively.

Authors

Li He (ORCID: https://orcid.org/0000-0002-5324-8101)
Xiatao Huang (ORCID: https://orcid.org/0000-0002-9943-732X)
Yifeng Xiong (ORCID: https://orcid.org/0000-0002-4290-7116)
Bo Liu (ORCID: https://orcid.org/0000-0002-1150-3709)
Xingang Huang
Weiliang Zhang (ORCID: https://orcid.org/0000-0002-9382-2374)

Institutions

ZTE (China) (CN)

Publication Details

Published: 2024-11-02
DOI: https://doi.org/10.1109/acp/ipoc63121.2024.10809477
Primary Topic: Digital Media Forensic Detection
Type: article
Field-Weighted Citation Impact: 0.00

Controls

|||

ALL TIME

JAN

FEB

MAR

APR

MAY

JUN

JUL

AUG

SEP

OCT

article

First Verification of Rogue ONU Recognition in Commercial GPON System Based on Machine Learning

Li He, Xiatao Huang, Yifeng Xiong, Bo Liu et al.

Nov 2, 2024

Digital Media Forensic Detection

article

First Verification of Rogue ONU Recognition in Commercial GPON System Based on Machine Learning

Li He, Xiatao Huang, Yifeng Xiong, Bo Liu, Xingang Huang, Weiliang Zhang

November 2, 2024article en

Abstract

We first demonstrate rogue ONU identification in commercial GPON system with waveform feature extraction. The experimental results show that the average identification accuracy can reach 90.69%/92.95%/96.57%/99.37% within 32 ONUs for Random Forest/KNN/CNN/ResNet, respectively.

ZTE (China) (CN)

Partnerships for the goals

Openalex Percentile: Top 75%

Digital Media Forensic Detection

DOI Source OpenAlex

AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.