Next Article in Journal
Influence of Wake Sweeping Frequency on the Unsteady Flow Characteristics of an Integrated Aggressive Interturbine Duct
Next Article in Special Issue
Synthetic Generation of Realistic Signal Strength Data to Enable 5G Rogue Base Station Investigation in Vehicular Platooning
Previous Article in Journal
Explainable-AI in Automated Medical Report Generation Using Chest X-ray Images
 
 
Review
Peer-Review Record

A Study of Network Intrusion Detection Systems Using Artificial Intelligence/Machine Learning

Appl. Sci. 2022, 12(22), 11752; https://doi.org/10.3390/app122211752
by Patrick Vanin 1, Thomas Newe 1,2,*, Lubna Luxmi Dhirani 1,2, Eoin O’Connell 1,2, Donna O’Shea 2,3, Brian Lee 2,4 and Muzaffar Rao 1,2
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Appl. Sci. 2022, 12(22), 11752; https://doi.org/10.3390/app122211752
Submission received: 25 October 2022 / Revised: 11 November 2022 / Accepted: 15 November 2022 / Published: 18 November 2022
(This article belongs to the Special Issue Information Security and Privacy)

Round 1

Reviewer 1 Report

1. Authors proposed an article entitled: "A Study of Network Intrusion Detection Systems using Machine Learning".

This is an interesting topic in the field of computer security. However, this article reviewed not only machine learning but deep learning as well. For the reason, it might be better if the title of the article is changed from machine learning to artificial intelligence.. 

2. Please add a column about the types of attacks prevented by the proposed IDSs. Also add a discussion about the effect of attacks they wanted to prevent.

3. Please reduce the similarity index of this article.

Comments for author File: Comments.pdf

Author Response

The response to comments is in the attached file. 

Author Response File: Author Response.docx

Reviewer 2 Report

This paper presents a nice overview of existing research in the field of IDS. The authors have put a lot of effort into analyzing the existing proposed solutions and showing the advantages and disadvantages of some of them. In this sense, I believe this work can be useful for researchers who want to make further strides in this field.

However, I would suggest a few changes. Several figures are not illustrative because they are fully presented in the text itself (Fig. 1, Fig. 2, Fig. 5). I suggest these images be removed.

In line 150, the authors say: "...Recall: Corresponds to the ratio of all attack samples to...". Should it be "correctly predicted attack samples" instead? Or is the formula below incorrect?

The authors should elaborate more on the cases when the probability is equal to zero (line 383).

In Table 3, the text "et.al" is duplicated everywhere.

Descriptions of datasets from Section 6 should precede Section 5.

It should be 40% instead of 60% in line 785?

Author Response

The response to comments is in the attached file. 

Author Response File: Author Response.docx

Reviewer 3 Report

The following revisions are required.

1. In literature review, add 3 to five more relevant and latest techniques.

2. Add 3 to 4 more techniques in table 3 at the end of literature review.

3. Please make sure your paper has necessary language proof-reading.

Author Response

The response to comments is in the attached file. 

Author Response File: Author Response.docx

Back to TopTop