Analysis and Detection of DDoS Backscatter Using NetFlow Data, Hyperband-Optimised Deep Learning and Explainability Techniques

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F63839172%3A_____%2F23%3A10133547" target="_blank" >RIV/63839172:_____/23:10133547 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-23492-7_8" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-23492-7_8</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-23492-7_8" target="_blank" >10.1007/978-3-031-23492-7_8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Analysis and Detection of DDoS Backscatter Using NetFlow Data, Hyperband-Optimised Deep Learning and Explainability Techniques

Popis výsledku v původním jazyce

The Denial of Service attacks are one of the most common attacks used to disrupt the services of public institutions. The criminal act of exhausting a network resource with the intent to obstruct the utility of a service is associated with hacktivism, blackmailing and extortion attempts. Intrusion Prevention Systems are an essential line of defence against this problem, strengthening public institutions, industrial and critical infrastructure alike. In the following work, an analysis of the detection of DDoS Backscatter with the use of neural networks is performed. To this end, a novel dataset is collected and described, on which a hyperband-optimized neural network is trained, and the decision process of the classifier is explained using LIME and SHAP.

Název v anglickém jazyce

Analysis and Detection of DDoS Backscatter Using NetFlow Data, Hyperband-Optimised Deep Learning and Explainability Techniques

Popis výsledku anglicky

The Denial of Service attacks are one of the most common attacks used to disrupt the services of public institutions. The criminal act of exhausting a network resource with the intent to obstruct the utility of a service is associated with hacktivism, blackmailing and extortion attempts. Intrusion Prevention Systems are an essential line of defence against this problem, strengthening public institutions, industrial and critical infrastructure alike. In the following work, an analysis of the detection of DDoS Backscatter with the use of neural networks is performed. To this end, a novel dataset is collected and described, on which a hyperband-optimized neural network is trained, and the decision process of the classifier is explained using LIME and SHAP.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LM2023054" target="_blank" >LM2023054: e-Infrastruktura CZ</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Artificial Intelligence and Soft Computing, Lecture Notes in Computer Science, vol 13588.

ISBN

978-3-031-23491-0

ISSN

2945-9133

e-ISSN

—

Počet stran výsledku

10

Strana od-do

82-92

Název nakladatele

Springer, Cham

Místo vydání

Neuveden

Místo konání akce

Zakopane, Polsko

Datum konání akce

19. 6. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000972696000008