kumoh national institute of technology
Networked Systems Lab.

Investigating Network Intrusion Detection Datasets Using Machine Learning (Accepted)
By :
Date : 2020-09-14
Views : 50

--------------- Reviews ------------------------------------

======= Review 1 =======

> *** Relevance: How well does the content fit the conference scope? Is this paper handling an important theme in this area?
Average(3)

> *** Completeness: Does this paper describe the problem clearly? Are the results of this paper reproducible via experiments (implementations, proofs)? How well is the result analysis done with the previous works? How clear is the paper's conclusion for the problem tackled?
Average(3)

> *** Originality: Does this paper include any novel approaches or new applications that have never been tried?
Marginal (2)

> *** Presentation: Are the title, abstract, and keywords appropriate? How proper is the organization and description method of this paper?
Average(3)

> *** Comments to authors: Please provide detailed comments to the authors.

This paper proposed a method to train the dataset of Network Intrusion Detection based on Deep Neural Networks. The training models of the related works mentioned in the paper are mostly only for one dataset. However, the model proposed by the authors is more versatile which can effectively train three different types of intrusion detection datasets, and get a good hit rate.

The paper is well-structured. The layers of DNN are clear. Terms are clearly explained and easily understood, but regarding the method of DNN, the innovation is not enough. Most of the paper only mentioned what to do, but did not say how to do it (e.g. hidden layer weights).

There are some typos and grammatical errors. On page 2, the 7th line, there is a mistake in the text. On page 3, the 3rd line, there is a typo (datsset).

> *** Recommendation: Please provide your overall recommendation on the acceptance of the paper. (Final acceptance decisions will also consider literal responses to the questions below.)
Reject (1)

======= Review 2 =======

> *** Relevance: How well does the content fit the conference scope? Is this paper handling an important theme in this area?
Average (3)

> *** Completeness: Does this paper describe the problem clearly? Are the results of this paper reproducible via experiments (implementations, proofs)? How well is the result analysis done with the previous works? How clear is the paper's conclusion for the problem tackled?
Average (3)

> *** Originality: Does this paper include any novel approaches or new applications that have never been tried?
Average (3)

> *** Presentation: Are the title, abstract, and keywords appropriate? How proper is the organization and description method of this paper?
Average (3)


> *** Recommendation: Please provide your overall recommendation on the acceptance of the paper. (Final acceptance decisions will also consider literal responses to the questions below.)
Weak Accept (3)

======= Review 3 =======

> *** Relevance: How well does the content fit the conference scope? Is this paper handling an important theme in this area?
Good (4)

> *** Completeness: Does this paper describe the problem clearly? Are the results of this paper reproducible via experiments (implementations, proofs)? How well is the result analysis done with the previous works? How clear is the paper's conclusion for the problem tackled?
Average (3)

> *** Originality: Does this paper include any novel approaches or new applications that have never been tried?
Average (3)

> *** Presentation: Are the title, abstract, and keywords appropriate? How proper is the organization and description method of this paper?
Good (4)


> *** Recommendation: Please provide your overall recommendation on the acceptance of the paper. (Final acceptance decisions will also consider literal responses to the questions below.)
Weak Accept (3)