Systematic Review on Identification and Prediction of Deep Learning-Based Cyber Security Technology and Convergence Fields

Round 1

Reviewer 1 Report

Some comments:

a. Acronyms in Abstract must be spelled.

b. Figures quality must be improved.

c. A discussion section could be added in the revised version of the manuscript. I could not detect it in the current version. 

d. The main limitations detected in the area should be added at the end of the manuscript, Conclusions section.

e. The manuscript looks like a review. In this sense, it must be declare it in the title of the paper.

f. A table with the main references consulted should be add.

g. English typos should be checked and improved in the revised version of the manuscript.

In my opinion, reconsideration after major revision. Thank you!

Author Response

We appreciate your comments. We believe that the comments have helped us improve the quality of our paper.

1. Acronyms in Abstract must be spelled.
   
   • According to the reviewers' opinions, Spelling of Acronyms in abstract was specified
2. Figures quality must be improved.
   • According to the reviewers' opinions, low-quality pictures among the pictures in the paper were improved and supplemented.According to the reviewers' opinions, low-quality pictures among the pictures in the paper were improved and supplemented.
3. A discussion section could be added in the revised version of the manuscript. I could not detect it in the current version. 
   • According to the reviewers' opinions, we added discussion in section 2.4. and we supplement the discussion, as well as key contributions and insights of this study in Section 2.4.
4. The main limitations detected in the area should be added at the end of the manuscript, Conclusions section.
   • According to the reviewers' opinions, we added a major limitation in the Conclusion section.
5. The manuscript looks like a review. In this sense, it must be declare it in the title of the paper.
   • According to the reviewers' opinions, the title of the paper has been revised.
6. A table with the main references consulted should be add.
   • According to the reviewers' opinions, We added main references to tables and figures.
7. English typos should be checked and improved in the revised version of the manuscript.
   • According to the reviewers' opinions, English typos in the entire paper were checked and improved. also, This paper has been proofread again by native-speaker editors in a related field to improve the writing style

 

Author Response File: Author Response.docx

Reviewer 2 Report

This paper investigated the changes and trends in cybersecurity convergence fields and technologies using probabilistic topic model techniques. Based on the analysis, the corresponding results are given. However, there are still some problems that need to be modified to improve the paper.

1. The overall organization of the paper needs to be improved.
2. The connections between paragraphs of the paper are a bit fragmented.
3. There are many relevent references not mentioned in the introduction. For example, considering the deception attacks on sensors, the stability under attacks should also be analyzed first. Different attacked sensors and actuators will cause different performance degeneration and even instability. On the centralized fusion under attacks , "The vulnerability of cyber-physical system under stealthy attacks[J]. IEEE Transactions on Automatic Control, 2020, 66(2): 637-650." gave a complete analysis on the vulnerability. On the distributed fusion under attacks, "The vulnerability of distributed state estimator under stealthy attacks[J]. Automatica, 2021, 133: 109869." discussed the stability.
4. The contributions of the paper are not highlighted.
5. The theoretical derivation and analysis of the algorithm for solving the problem are not demonstrated in the paper.

Author Response

 We appreciate your comments. We believe that the comments have helped us improve the quality of our paper. This paper has been proofread again by native-speaker editors in a related field to improve the writing style.

1. The overall organization of the paper needs to be improved.
   • According to the reviewers' opinions, We have reorganized the overall flow of this paper and specified the composition of the paper at the end of the introduction so that the reader can more easily understand the overall flow of the paper.
2. The connections between paragraphs of the paper are a bit fragmented.
   • According to the reviewers' opinions, We explained the relationship between each paragraph, section, and chapter, and rearranged the flow of the paragraph to increase the connectivity of the paper.
3. There are many relevent references not mentioned in the introduction. For example, considering the deception attacks on sensors, the stability under attacks should also be analyzed first. Different attacked sensors and actuators will cause different performance degeneration and even instability. On the centralized fusion under attacks , "The vulnerability of cyber-physical system under stealthy attacks[J]. IEEE Transactions on Automatic Control, 2020, 66(2): 637-650." gave a complete analysis on the vulnerability. On the distributed fusion under attacks, "The vulnerability of distributed state estimator under stealthy attacks[J]. Automatica, 2021, 133: 109869." discussed the stability.
   • According to the reviewers' opinions, two papers("The vulnerability of cyber-physical system under stealthy attacks[J]. IEEE Transactions on Automatic Control, 2020, 66(2): 637-650.", "The vulnerability of distributed state estimator under stealthy attacks[J]. Automatica, 2021, 133: 109869.") were referenced. These papers will be important relevant references in our paper.
4. The contributions of the paper are not highlighted.

   • According to the reviewers' opinions, we added contributions in section 2.4. and we supplement the discussion, as well as key discussion and insights of this study in Section 2.4.

5. The theoretical derivation and analysis of the algorithm for solving the problem are not demonstrated in the paper.

   • According to the reviewer's opinion, the theoretical derivation and analysis of the deep learning algorithms (LDA, DTM, LSTM) used in the experiments of this paper were supplemented in Section 3.2. In addition, explanations of how each algorithm is used in this paper are also supplemented in each section. For example, LDA is described in Section 4.3, DTM in Sections 4.4 and 5.1, and finally, LSTM is described in Section 5.2.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Some comments:

a. The quality of Figure 2 and Figure 9 and 10 is not adequated. Please, improve in the revised version.

b. Please, include limitations of the research work in conclusions section.

c. Please, remark clearly the benefits of this research work in terms of the current state-of-the-art.

d. Which is the main innovation and/or novelty of this research work? This sentence "In this respect, analysis of papers and patents is a useful way to provide an overview of the novelty and innovativeness of various technologies in the field of cyber security" give no information about that.

Author Response

We appreciate your comments. We believe that the comments have helped us improve the quality of our paper.

a. The quality of Figure 2 and Figure 9 and 10 is not adequated. Please, improve in the revised version.

• We improved the quality of the Figures(2 , 9 ,10) mentioned by reviewers

b. Please, include limitations of the research work in conclusions section.

• According to the reviewers' opinions, we added the limitations of the research work to the conclusion section.

c. Please, remark clearly the benefits of this research work in terms of the current state-of-the-art.

• According to the reviewers' opinions, The advantages of this study from the standpoint of state-of-the-art technology are described in Section 3.1, Introduction to the Research Process, of Chapter 3, Research Methodology.

d. Which is the main innovation and/or novelty of this research work? This sentence "In this respect, analysis of papers and patents is a useful way to provide an overview of the novelty and innovativeness of various technologies in the field of cyber security" give no information about that.

• According to the reviewers' opinions, The innovation and novelty of the work of this research was added to the conclusion.

Author Response File: Author Response.docx

Reviewer 2 Report

I have no further comment.

Author Response

We appreciate your comments. We believe that the comments have helped us improve the quality of our paper.

This paper has been proofread again by native-speaker editors in a related field to improve the writing style

Author Response File: Author Response.docx

Round 3

Reviewer 1 Report

I have no additional comments.