Skip to main content

Table 3 Done experiments on IDS optimization using big data

From: Big data analysis and distributed deep learning for next-generation intrusion detection system optimization

Name

OSI layer

Time of detection

Data sources

Detection technique

Big data environment

Used data set

Beehive [20]

7

Non-real

Proxy logs

k-means

Hadoop, Hive

Operational network

Bumgardner and Marek [21]

3, 4

Real-time

Network flows

Threshold

Storm, HBase, Hadoop

Operational network

Camacho et al. [22]

7, 4, 3

Non-real

Firewall and IDS logs

PCA

Custom

Public dataset

Dromard et al. [23]

4, 3

Non-real

Network flows

DBSCAN

Spark

Operational network

Giura and Wang [24]

7, 4, 3

Non-real

Network and application data

Threshold

Hadoop

Operational network

Gupta and Kulariya [25]

7, 4, 3

Non-real

Network captures

Several feature extraction and classification algorithms

Spark

Public dataset

Gonc¸alves et al. [26]

3, 4, 7

Non-real

DHCP, Authentication and Firewall logs

EM

Hadoop, Weka

Operational network

Hashdoop [27]

Packet captures

Non-real

Network traffic

 

Hadoop

Public dataset

Iturbe et al. [19]

 

Non-real

Network flows

Whitelisting

Elastics Search

Operational network

Marchal et al. [28]

3, 4, 7

Non-real

Honeypot, DNS, HTTP, Network flow data

Threshold

Hadoop, Hive, Pig, Spark

Operational network

MATATABI [29]

3, 4, 7

Non-real

DNS records, Network flows, Spam email

Multiple classification algorithms

Hive

Operational network

Rathore et al. [30]

3, 4

Non-real

Network flows

C4.5, RepTree

Spark, Weka

Public dataset

Ratner and Kelly [31]

Packet captures

Non-real

Network packets

Manual data querying

Hadoop

Operational network

Therdphapiyanak and Piromsopa [32]

7, 4, 3

Non-real

Network logs

k-means

Hadoop, Mahout

Public dataset

TADOOP [33]

3, 4

Non-real

Network flows

DTE-FP

Hadoop

Operational network

Wang et al. [34]

3, 4

Real-time

Network flows

Intergroup entropy, LMS

Storm

Operational network

Xu et al. [35]

7

Non-real

Console logs

PCA

Hadoop

Operational network

Hadziosmanovic et al. [36]

 

Non-real

SCADA logs

FP-Graph

Custom

Operational network

Difallah et al. [37]

 

Real-time

Process data

LISA

Storm

Simulated process data

Wallace et al. [38]

 

Real-time

Process data

Cumulative probability distribution

Spark

Operational network

Kiss et al. [39]

 

Non-real

Process data

k-means

Hadoop

Simulated process data

Hurst et al. [40]

 

Non-real

Process data

Multiple classification algorithms

Custom

Simulated process data