Human error tolerant anomaly detection based on time-periodic packet sampling

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper focuses on an anomaly detection method that uses a baseline model describing the normal behavior of network traffic as the basis for comparison with the audit network traffic. In the anomaly detection method, an alarm is raised if a pattern in the current network traffic deviates from the baseline model. The baseline model is often trained using normal traffic data extracted from traffic data for which all instances (i.e.; packets) are manually labeled by human experts in advance as either normal or anomalous. However, since humans are fallible, some errors are inevitable in labeling traffic data. Therefore, in this paper, we propose an anomaly detection method that is tolerant to human errors in labeling traffic data. The fundamental idea behind the proposed method is to take advantage of the lossy nature of packet sampling for the purpose of correcting/preventing human errors in labeling traffic data. By using real traffic traces, we show that the proposed method can better detect anomalies regarding TCP SYN packets than the method that relies only on human labeling.

Original languageEnglish
Pages (from-to)242-250
Number of pages9
JournalKnowledge-Based Systems
Volume106
DOIs
Publication statusPublished - 2016 Aug 15
Externally publishedYes

Fingerprint

Labeling
Sampling
Anomaly detection
Human error

Keywords

  • Anomaly detection
  • Human error
  • Packet sampling

ASJC Scopus subject areas

  • Software
  • Management Information Systems
  • Information Systems and Management
  • Artificial Intelligence

Cite this

Human error tolerant anomaly detection based on time-periodic packet sampling. / Uchida, Masato.

In: Knowledge-Based Systems, Vol. 106, 15.08.2016, p. 242-250.

Research output: Contribution to journalArticle

@article{a5aa5bfa9e2a4a93817556fe8e272089,
title = "Human error tolerant anomaly detection based on time-periodic packet sampling",
abstract = "This paper focuses on an anomaly detection method that uses a baseline model describing the normal behavior of network traffic as the basis for comparison with the audit network traffic. In the anomaly detection method, an alarm is raised if a pattern in the current network traffic deviates from the baseline model. The baseline model is often trained using normal traffic data extracted from traffic data for which all instances (i.e.; packets) are manually labeled by human experts in advance as either normal or anomalous. However, since humans are fallible, some errors are inevitable in labeling traffic data. Therefore, in this paper, we propose an anomaly detection method that is tolerant to human errors in labeling traffic data. The fundamental idea behind the proposed method is to take advantage of the lossy nature of packet sampling for the purpose of correcting/preventing human errors in labeling traffic data. By using real traffic traces, we show that the proposed method can better detect anomalies regarding TCP SYN packets than the method that relies only on human labeling.",
keywords = "Anomaly detection, Human error, Packet sampling",
author = "Masato Uchida",
year = "2016",
month = "8",
day = "15",
doi = "10.1016/j.knosys.2016.05.050",
language = "English",
volume = "106",
pages = "242--250",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",

}

TY - JOUR

T1 - Human error tolerant anomaly detection based on time-periodic packet sampling

AU - Uchida, Masato

PY - 2016/8/15

Y1 - 2016/8/15

N2 - This paper focuses on an anomaly detection method that uses a baseline model describing the normal behavior of network traffic as the basis for comparison with the audit network traffic. In the anomaly detection method, an alarm is raised if a pattern in the current network traffic deviates from the baseline model. The baseline model is often trained using normal traffic data extracted from traffic data for which all instances (i.e.; packets) are manually labeled by human experts in advance as either normal or anomalous. However, since humans are fallible, some errors are inevitable in labeling traffic data. Therefore, in this paper, we propose an anomaly detection method that is tolerant to human errors in labeling traffic data. The fundamental idea behind the proposed method is to take advantage of the lossy nature of packet sampling for the purpose of correcting/preventing human errors in labeling traffic data. By using real traffic traces, we show that the proposed method can better detect anomalies regarding TCP SYN packets than the method that relies only on human labeling.

AB - This paper focuses on an anomaly detection method that uses a baseline model describing the normal behavior of network traffic as the basis for comparison with the audit network traffic. In the anomaly detection method, an alarm is raised if a pattern in the current network traffic deviates from the baseline model. The baseline model is often trained using normal traffic data extracted from traffic data for which all instances (i.e.; packets) are manually labeled by human experts in advance as either normal or anomalous. However, since humans are fallible, some errors are inevitable in labeling traffic data. Therefore, in this paper, we propose an anomaly detection method that is tolerant to human errors in labeling traffic data. The fundamental idea behind the proposed method is to take advantage of the lossy nature of packet sampling for the purpose of correcting/preventing human errors in labeling traffic data. By using real traffic traces, we show that the proposed method can better detect anomalies regarding TCP SYN packets than the method that relies only on human labeling.

KW - Anomaly detection

KW - Human error

KW - Packet sampling

UR - http://www.scopus.com/inward/record.url?scp=84975159445&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975159445&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2016.05.050

DO - 10.1016/j.knosys.2016.05.050

M3 - Article

VL - 106

SP - 242

EP - 250

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

ER -