Utilizing Duplicate Announcements for BGP Anomaly Detection

The Border Gateway Protocol (BGP) is the backbone of inter-domain routing on the internet, but its susceptibility to both benign and malicious anomalies creates substantial risks to both network reliability and security. In this study, we present a new approach for deep learning-based BGP anomaly de...

Full description

Saved in:
Bibliographic Details
Main Authors: Rahul Deo Verma, Pankaj Kumar Keserwani, Vinesh Kumar Jain, Mahesh Chandra Govil, Valmik Tilwari
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Telecom
Subjects:
Online Access:https://www.mdpi.com/2673-4001/6/1/11
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850088162536194048
author Rahul Deo Verma
Pankaj Kumar Keserwani
Vinesh Kumar Jain
Mahesh Chandra Govil
Valmik Tilwari
author_facet Rahul Deo Verma
Pankaj Kumar Keserwani
Vinesh Kumar Jain
Mahesh Chandra Govil
Valmik Tilwari
author_sort Rahul Deo Verma
collection DOAJ
description The Border Gateway Protocol (BGP) is the backbone of inter-domain routing on the internet, but its susceptibility to both benign and malicious anomalies creates substantial risks to both network reliability and security. In this study, we present a new approach for deep learning-based BGP anomaly detection utilizing duplicate announcements, which are known to be a symptom of routing disruptions. We developed our methodology based on public BGP data from RIPE and Route Views. We used the number of duplicate announcements as a baseline against which we checked for sporadic and time-based anomalies. Here, we propose a deep learning framework based on the Exponential Moving Average (EMA) model in combination with Autoencoder for anomaly identification. We also apply the Temporal-oriented Synthetic Minority Over-Sampling Technique (T-SMOTE) to overcome data imbalance. Comparative evaluations show that the Autoencoder model is significantly better than LSTM and that existing state-of-the-art methods have higher accuracy, precision, recall, and F1 scores. This study proposes a reliable, scalable, and rapid framework for real-time BGP adversary detection, which improves network security and resilience.
format Article
id doaj-art-4bde173d98964c29b4e88b425fe35e88
institution DOAJ
issn 2673-4001
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Telecom
spelling doaj-art-4bde173d98964c29b4e88b425fe35e882025-08-20T02:43:04ZengMDPI AGTelecom2673-40012025-02-01611110.3390/telecom6010011Utilizing Duplicate Announcements for BGP Anomaly DetectionRahul Deo Verma0Pankaj Kumar Keserwani1Vinesh Kumar Jain2Mahesh Chandra Govil3Valmik Tilwari4Department of Computer Science and Engineering, National Institute of Technology, Ravangla 737139, Sikkim, IndiaDepartment of Computer Science and Engineering, National Institute of Technology, Ravangla 737139, Sikkim, IndiaDepartment of Computer Engineering, Government Engineering College, Ajmer 305025, Rajasthan, IndiaDepartment of Computer Science and Engineering, National Institute of Technology, Ravangla 737139, Sikkim, IndiaElectrical Engineering Department, Korea University, Seoul 02841, Republic of KoreaThe Border Gateway Protocol (BGP) is the backbone of inter-domain routing on the internet, but its susceptibility to both benign and malicious anomalies creates substantial risks to both network reliability and security. In this study, we present a new approach for deep learning-based BGP anomaly detection utilizing duplicate announcements, which are known to be a symptom of routing disruptions. We developed our methodology based on public BGP data from RIPE and Route Views. We used the number of duplicate announcements as a baseline against which we checked for sporadic and time-based anomalies. Here, we propose a deep learning framework based on the Exponential Moving Average (EMA) model in combination with Autoencoder for anomaly identification. We also apply the Temporal-oriented Synthetic Minority Over-Sampling Technique (T-SMOTE) to overcome data imbalance. Comparative evaluations show that the Autoencoder model is significantly better than LSTM and that existing state-of-the-art methods have higher accuracy, precision, recall, and F1 scores. This study proposes a reliable, scalable, and rapid framework for real-time BGP adversary detection, which improves network security and resilience.https://www.mdpi.com/2673-4001/6/1/11machine learningborder gateway protocolanomaly detectionduplicate announcementsprefix hijackingnetwork security
spellingShingle Rahul Deo Verma
Pankaj Kumar Keserwani
Vinesh Kumar Jain
Mahesh Chandra Govil
Valmik Tilwari
Utilizing Duplicate Announcements for BGP Anomaly Detection
Telecom
machine learning
border gateway protocol
anomaly detection
duplicate announcements
prefix hijacking
network security
title Utilizing Duplicate Announcements for BGP Anomaly Detection
title_full Utilizing Duplicate Announcements for BGP Anomaly Detection
title_fullStr Utilizing Duplicate Announcements for BGP Anomaly Detection
title_full_unstemmed Utilizing Duplicate Announcements for BGP Anomaly Detection
title_short Utilizing Duplicate Announcements for BGP Anomaly Detection
title_sort utilizing duplicate announcements for bgp anomaly detection
topic machine learning
border gateway protocol
anomaly detection
duplicate announcements
prefix hijacking
network security
url https://www.mdpi.com/2673-4001/6/1/11
work_keys_str_mv AT rahuldeoverma utilizingduplicateannouncementsforbgpanomalydetection
AT pankajkumarkeserwani utilizingduplicateannouncementsforbgpanomalydetection
AT vineshkumarjain utilizingduplicateannouncementsforbgpanomalydetection
AT maheshchandragovil utilizingduplicateannouncementsforbgpanomalydetection
AT valmiktilwari utilizingduplicateannouncementsforbgpanomalydetection