DoS Attack Detection Using Edge Machine Learning

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shende, Rutuja, Narwade, Yuvraj, Shitole, Sanket, Kute, Om, Prof. T. B. Faruki
Format: Recurso digital
Sprache:Englisch
Veröffentlicht: Zenodo 2025
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866901470272552960
author Shende, Rutuja
Narwade, Yuvraj
Shitole, Sanket
Kute, Om
Prof. T. B. Faruki
author_facet Shende, Rutuja
Narwade, Yuvraj
Shitole, Sanket
Kute, Om
Prof. T. B. Faruki
contents <p><span lang="EN-GB">A Distributed Denial of Service (DDoS) attack is an attempt to make a service unavailable by overwhelming the server with malicious traffic. DDoS attacks have become the most tedious and cumber some issue in recent past. The number and magnitude of attacks have increased from few megabytes of data to 100s of terabytes of data these days. Due to the differences in the attack patterns or new types of attack, it is hard to detect these attacks effectively. In this paper, we devise new techniques for causing DDoS attacks and mitigation which are clearly shown to perform much better than the existing techniques. We also categorize DDoS attack techniques as well as the techniques used in their detection and thus attempt an extensive scoping of the DDoS problem. We also compare our attack module with a couple of tools available.</span></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_17614142
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle DoS Attack Detection Using Edge Machine Learning
Shende, Rutuja
Narwade, Yuvraj
Shitole, Sanket
Kute, Om
Prof. T. B. Faruki
<p><span lang="EN-GB">A Distributed Denial of Service (DDoS) attack is an attempt to make a service unavailable by overwhelming the server with malicious traffic. DDoS attacks have become the most tedious and cumber some issue in recent past. The number and magnitude of attacks have increased from few megabytes of data to 100s of terabytes of data these days. Due to the differences in the attack patterns or new types of attack, it is hard to detect these attacks effectively. In this paper, we devise new techniques for causing DDoS attacks and mitigation which are clearly shown to perform much better than the existing techniques. We also categorize DDoS attack techniques as well as the techniques used in their detection and thus attempt an extensive scoping of the DDoS problem. We also compare our attack module with a couple of tools available.</span></p>
title DoS Attack Detection Using Edge Machine Learning
url https://doi.org/10.5281/zenodo.17614142