Leveraging siamese networks for one-shot intrusion detection model

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00361070" target="_blank" >RIV/68407700:21230/23:00361070 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/s10844-022-00747-z" target="_blank" >https://doi.org/10.1007/s10844-022-00747-z</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10844-022-00747-z" target="_blank" >10.1007/s10844-022-00747-z</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Leveraging siamese networks for one-shot intrusion detection model

Popis výsledku v původním jazyce

The use of supervised Machine Learning (ML) to enhance Intrusion Detection Systems (IDS) has been the subject of significant research. Supervised ML is based upon learning by example, demanding significant volumes of representative instances for effective training and the need to retrain the model for every unseen cyber-attack class. However, retraining the models in-situ renders the network susceptible to attacks owing to the time-window required to acquire a sufficient volume of data. Although anomaly detection systems provide a coarse-grained defence against unseen attacks, these approaches are significantly less accurate and suffer from high false-positive rates. Here, a complementary approach referred to as "One-Shot Learning", whereby a limited number of examples of a new attack-class is used to identify a new attack-class (out of many) is detailed. The model grants a new cyber-attack classification opportunity for classes that were not seen during training without retraining. A Siamese Network is trained to differentiate between classes based on pairs similarities, rather than features, allowing to identify new and previously unseen attacks. The performance of a pre-trained model to classify new attack-classes based only on one example is evaluated using three mainstream IDS datasets; CICIDS2017, NSL-KDD, and KDD Cup'99. The results confirm the adaptability of the model in classifying unseen attacks and the trade-off between performance and the need for distinctive class representations.

Název v anglickém jazyce

Leveraging siamese networks for one-shot intrusion detection model

Popis výsledku anglicky

The use of supervised Machine Learning (ML) to enhance Intrusion Detection Systems (IDS) has been the subject of significant research. Supervised ML is based upon learning by example, demanding significant volumes of representative instances for effective training and the need to retrain the model for every unseen cyber-attack class. However, retraining the models in-situ renders the network susceptible to attacks owing to the time-window required to acquire a sufficient volume of data. Although anomaly detection systems provide a coarse-grained defence against unseen attacks, these approaches are significantly less accurate and suffer from high false-positive rates. Here, a complementary approach referred to as "One-Shot Learning", whereby a limited number of examples of a new attack-class is used to identify a new attack-class (out of many) is detailed. The model grants a new cyber-attack classification opportunity for classes that were not seen during training without retraining. A Siamese Network is trained to differentiate between classes based on pairs similarities, rather than features, allowing to identify new and previously unseen attacks. The performance of a pre-trained model to classify new attack-classes based only on one example is evaluated using three mainstream IDS datasets; CICIDS2017, NSL-KDD, and KDD Cup'99. The results confirm the adaptability of the model in classifying unseen attacks and the trade-off between performance and the need for distinctive class representations.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název periodika

Journal of Intelligent Information Systems

ISSN

0925-9902

e-ISSN

1573-7675

Svazek periodika

60

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

30

Strana od-do

407-436

Kód UT WoS článku

000879127600001

EID výsledku v databázi Scopus

2-s2.0-85141377999