2017
DOI: 10.1007/978-3-319-66332-6_6
|View full text |Cite
|
Sign up to set email alerts
|

ILAB: An Interactive Labelling Strategy for Intrusion Detection

Abstract: Abstract. Acquiring a representative labelled dataset is a hurdle that has to be overcome to learn a supervised detection model. Labelling a dataset is particularly expensive in computer security as expert knowledge is required to perform the annotations. In this paper, we introduce ILAB, a novel interactive labelling strategy that helps experts label large datasets for intrusion detection with a reduced workload. First, we compare ILAB with two state-of-the-art labelling strategies on public labelled datasets… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
16
0
15

Year Published

2018
2018
2023
2023

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 25 publications
(33 citation statements)
references
References 35 publications
0
16
0
15
Order By: Relevance
“…al. introduce ILAB [7] as an active learning method for intrusion detection. Our work differs in using active learning guided by a boosting classifier and a naïve bayes anomaly detector, applied to command embedding representation, with the goal of detecting LOL attacks that leverage existing Windows tools.…”
Section: Related Workmentioning
confidence: 99%
“…al. introduce ILAB [7] as an active learning method for intrusion detection. Our work differs in using active learning guided by a boosting classifier and a naïve bayes anomaly detector, applied to command embedding representation, with the goal of detecting LOL attacks that leverage existing Windows tools.…”
Section: Related Workmentioning
confidence: 99%
“…Varios autores [97,5,37,49] estiman que el uso de humanos expertos es esencial en el análisis de tráfico y posterior etiquetado de conexiones. Debido a que los expertos en redes son un recurso caro, el proceso de etiquetado debe utilizar el tiempo de estos usuarios de manera eficiente.…”
Section: Etiquetado Manualunclassified
“…De igual manera, Görnitz utiliza un enfoque de vecinos cercanos (KNN del inglés k-nearest neighbors) para la identificación de estas familias de conexiones. Un paso más alla en el intento de acelerar el ciclo de trabajo de AL, el trabajo de Beaugnon et al [5] se basa en la detección de categorías raras para evitar el sesgo de muestreo, como en el caso de Stokes, pero con una estrategia de "divide y vencerás" para asegurar una buena interacción humano-computadora enfocado al etiquetado por pequeñas secciones del tráfico.…”
Section: Etiquetado Asistidounclassified
See 1 more Smart Citation
“…In Eventpad we aim for an alternative approach where analysts can interactively define themselves which data attributes should be represented in what way to serve their task at best. With ILAB, Beaugnon et al [5] already illustrated the value of human interaction to incrementally label data instances for supervised intrusion detection models. Systems such as KAMAS [29,36] also use rules to search for patterns in call sequences, but limit their sequential analysis to only this attribute.…”
Section: Malware Discoverymentioning
confidence: 99%