Intrusion Detection Techniques in Social Media Cloud: Review and Future Directions

Table 3

Statistical method review table.

Reference	Methodology	Dataset	Result
[26]	Determining thresholds for network parameters	Benchmark DARPA	It can effectively evaluate vulnerability and detect intrusion from raw network data
[27]	PCA, chi-square distribution, and Gaussian mixture distribution	Real network traffic	PCA and Gaussian mixed distributions reached 97.5 percent detection rate each, whereas the chi-square distribution reached 90 percent
[28]	Continually monitors incoming network packets using the active ports of each host in a network as sensors	Real network traffic	Produced good results
[29]	The least square support vector machine (LS-SVM)	KDD CUP 99	It is effective for detecting intrusions in static and scalable datasets
[30]	GA	KDD CUP 99	Higher detection rate of 99.4 percent
[31]	The hybrid classifier (DTNB) is a combination of the DT and naïve Bayes (NB) algorithms	NSL-KDD	High detection rate