ANOMALY DETECTION IN NETWORK TRAFFIC USING A HYBRID MODEL OF K-MEANS CLUSTERING AND AUTOENCODERS
Fuente:
Zenodo
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Recurso digital |
| Publié: |
Zenodo
2025
|
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866901851092287488 |
|---|---|
| author | Apurva Kishor Gawde and Sunita Jena |
| author_facet | Apurva Kishor Gawde and Sunita Jena |
| contents | <p>ABSTRACT <br>Anomaly detection is generally understood to refer to rare objects, events or observations that deviate <br>significantly from the bulk of the data and do not conform to well-defined notions of normal practice. The model <br>uses the k-means power of clustering to identify potential anomalies based on the distance between cluster <br>centroids and optimizes the search by using an autoencoder to detect reconstruction errors and then, hybrid <br>method combining kmeans and autoencoder, compared with individual methods . The model was tested on real<br>time network traffic data collected through Wireshark, which demonstrated its effectiveness in detecting <br>anomalous networks. KMeans and Autoencoders have been shown to perform well in detecting anomalies in <br>network traffic, where both methods show the same number of anomalies and in addition, the hybrid method <br>detects fewer anomalies and outperforms both KMeans and Autoencoders. <br>Keywords: Anomaly detection, K-Means, cyber security, autoencoders. </p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15681691 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | ANOMALY DETECTION IN NETWORK TRAFFIC USING A HYBRID MODEL OF K-MEANS CLUSTERING AND AUTOENCODERS Apurva Kishor Gawde and Sunita Jena <p>ABSTRACT <br>Anomaly detection is generally understood to refer to rare objects, events or observations that deviate <br>significantly from the bulk of the data and do not conform to well-defined notions of normal practice. The model <br>uses the k-means power of clustering to identify potential anomalies based on the distance between cluster <br>centroids and optimizes the search by using an autoencoder to detect reconstruction errors and then, hybrid <br>method combining kmeans and autoencoder, compared with individual methods . The model was tested on real<br>time network traffic data collected through Wireshark, which demonstrated its effectiveness in detecting <br>anomalous networks. KMeans and Autoencoders have been shown to perform well in detecting anomalies in <br>network traffic, where both methods show the same number of anomalies and in addition, the hybrid method <br>detects fewer anomalies and outperforms both KMeans and Autoencoders. <br>Keywords: Anomaly detection, K-Means, cyber security, autoencoders. </p> |
| title | ANOMALY DETECTION IN NETWORK TRAFFIC USING A HYBRID MODEL OF K-MEANS CLUSTERING AND AUTOENCODERS |
| url | https://doi.org/10.5281/zenodo.15681691 |