2017 IEEE 16th International Symposium on Network Computing and Applications (NCA) 2017
DOI: 10.1109/nca.2017.8171327
|View full text |Cite
|
Sign up to set email alerts
|

Diversity with intrusion detection systems: An empirical study

Abstract: Abstract-Defence-in-depth is a term often used in security literature to denote architectures in which multiple security protection systems are deployed to defend the valuable assets of an organization (e.g. the data and the services). In this paper we present an approach for analysing defence-in-depth, and illustrate the use of the approach with an empirical study in which we have assessed the detection capabilities of intrusion detection systems when deployed in diverse, two-version, parallel defence-in-dept… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
2
1
1

Relationship

1
3

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 13 publications
0
3
0
Order By: Relevance
“…In the future, it will likely be beneficial to deploy PULSAR on smart IDSs [134]. Second, while existing work uses outdated [120], [135], short-term [136], or limited variety of attack type datasets [137], [138], our source training data are longitudinal (representing 10-year) and have been collected in real production traffic with up-to-date attack activities (until 2018). Third, while deep-learning models, e.g., [90], are promising, they offer analysts few explanations on how the models work.…”
Section: Resultsmentioning
confidence: 99%
“…In the future, it will likely be beneficial to deploy PULSAR on smart IDSs [134]. Second, while existing work uses outdated [120], [135], short-term [136], or limited variety of attack type datasets [137], [138], our source training data are longitudinal (representing 10-year) and have been collected in real production traffic with up-to-date attack activities (until 2018). Third, while deep-learning models, e.g., [90], are promising, they offer analysts few explanations on how the models work.…”
Section: Resultsmentioning
confidence: 99%
“…The benefits of diversity between IDSs is empirically studied in [25], and they also provide numerical evidence demonstrating the advantages of using functionally similar IDSs. Our work differs from this as we evaluate the dynamic evolution of this diversity over four years.…”
Section: Related Workmentioning
confidence: 99%
“…The authors also discuss the metrics, evaluation criteria and the data sets that have been used in recent research works on IDSs. In Algaith and et al (2017), the authors show the benefits of using a diverse set of IDSs in an empirical study. The authors have shown the efficacy of diversity by deploying the IDSs in different configurations such that to minimize false negatives/positives.…”
Section: Related Workmentioning
confidence: 99%