2019 27th Signal Processing and Communications Applications Conference (SIU) 2019
DOI: 10.1109/siu.2019.8806451
|View full text |Cite
|
Sign up to set email alerts
|

Network Anomaly Detection Using Header Information With Greedy Algorithm

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
3
0
1

Year Published

2020
2020
2024
2024

Publication Types

Select...
3
2
1
1

Relationship

1
6

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 7 publications
0
3
0
1
Order By: Relevance
“…Even in processes that are tied to physical mediums, like, for example, nuclear radiation detection [30], telemetry data for spacecraft operations [31], traffic patterns analysis [32], sensor arrays and IoT systems [33], unmanned ground and aerial vehicles detection [34], edge computing systems and novel large-scale IT systems [35] or network quality of service assurance by using a Greedy algorithm [36] or even genetic algorithms [37], such ML algorithms can be used for identification of anomalies. Moreover, similar algorithms are used in domains like supply chain management, where genetic rule-based and graph-based detection methods are employed to verify business transactions regarding their validity [20].…”
Section: B Methods and Algorithms In Anomaly Detectionmentioning
confidence: 99%
“…Even in processes that are tied to physical mediums, like, for example, nuclear radiation detection [30], telemetry data for spacecraft operations [31], traffic patterns analysis [32], sensor arrays and IoT systems [33], unmanned ground and aerial vehicles detection [34], edge computing systems and novel large-scale IT systems [35] or network quality of service assurance by using a Greedy algorithm [36] or even genetic algorithms [37], such ML algorithms can be used for identification of anomalies. Moreover, similar algorithms are used in domains like supply chain management, where genetic rule-based and graph-based detection methods are employed to verify business transactions regarding their validity [20].…”
Section: B Methods and Algorithms In Anomaly Detectionmentioning
confidence: 99%
“…In contrast, the statistical method is employed on the live packet for analysis. For live traffic, the header field is the best source of information that can be used for detecting anomalies; the researchers in [33] did a study of the probability distribution function of different header fields for identifying anomalies in packets. The researcher in [34] discusses the use of packet header and payload histogram for the analysis of packets and to detect anomalies.…”
Section: Related Workmentioning
confidence: 99%
“…Ateş vd., (2019) çalışmalarında açgözlü algoritması (Greedy Algorithm) ve destek vektör makinelerinden (SVM) faydalanarak siber saldırıları tespit etmeye çalışmışlardır. İnceledikleri siber saldırı modeli DDOS olup veriler arasındaki uzaklıkları hesaplamak için açgözlü algoritmasından ve yanlış tepit oranını azaltmak için SVM sınıflandırma modelinden faydalanmışlardır [38]. Tok konusunda kullanıcı algısını elde edebilmek için bir anket çalışması gerçekleştirmişlerdir.…”
Section: Türki̇ye' De Si̇ber Suçlar Ve çöZüm Yöntemleri̇ üZeri̇ne Li̇teratür Taramasiunclassified