All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
I am pleased to inform you that your work has now been accepted for publication in PeerJ Computer Science.
Please be advised that you are not permitted to add or remove authors or references post-acceptance, regardless of the reviewers' request(s).
Thank you for submitting your work to this journal. On behalf of the Editors of PeerJ Computer Science, we look forward to your continued contributions to the Journal.
With kind regards,
[# PeerJ Staff Note - this decision was reviewed and approved by Sedat Akleylek, a PeerJ Section Editor covering this Section #]
All my basic reporting concerns have been addressed. The paper is now suitable for publication.
All my experimental design concerns have been addressed. The paper is now suitable for publication.
All my validity of findings concerns have been addressed. The paper is now suitable for publication.
All my concerns have been addressed. The paper is now suitable for publication.
I have received reviews of your manuscript from scholars who are experts on the cited topic. They find the topic very interesting; however, several concerns must be addressed regarding statistical analysis of the results, more performance metrics, experimental results with more (up-to-date) datasets, up-to-date references, and comparisons with current approaches. These issues require a major revision. Please refer to the reviewers’ comments listed at the end of this letter, and you will see that they are advising that you revise your manuscript. If you are prepared to undertake the work required, I would be pleased to reconsider my decision. Please submit a list of changes or a rebuttal against each point that is being raised when you submit your revised manuscript.
Thank you for considering PeerJ Computer Science for the publication of your research.
With kind regards,
Strengths
The article uses clear and unambiguous, professional English used throughout. The raw data for the algorithm and the source code for the algorithm are shared.
The article is has professional structure and is self-contained with relevant results to hypotheses.
Weaknesses
The literature references could be improved. Specifically the following pieces of recent research seem related:
The source code used to produce figures 2-7 should be shared. In addition, the figures should be placed more closely to the text discussing them. In the current version of the article the figures are almost embedded in the references section.
In addition, figures 3-8 rely on red/green color contrast. As many as 8% of males and 0.5% of females have some form of color-blindness, the most common being difficulty in perceiving the difference between the colors red and green. This means that potentially one out of 12 males and one out of 200 females who look at figures 3 and 4 will have difficulty comparing the different plotted lines. Several palettes designed around avoiding this issue are provided here: https://davidmathlogic.com/colorblind/#%23D81B60-%231E88E5-%23FFC107-%23004D40
Figure 1 does not use any color and would be improved to help elucidate it dynamics with a color safe palette.
All the tables that report decimal figures need to be right justified so that the significant digits in different rows can be compared across columns easily.
A thorough systematic review of related approaches to detecting DDOS attacks with deep learning and machine learning is described in the Mittal et al. paper. Describing their findings with respect to (i) the different types of DDoS attack detection deep learning approaches, (ii) the methodologies, strengths, and weaknesses of existing deep learning approaches for DDoS attacks detection (iii) benchmarked datasets and classes of attacks in datasets used in the existing literature, and (iv) the preprocessing strategies, hyperparameter values, experimental setups, and performance metrics used in the existing literature would help supplement Table 1.
Mittal, Meenakshi, Krishan Kumar, and Sunny Behal. "Deep learning approaches for detecting DDoS attacks: A systematic review." Soft Computing 27.18 (2023): 13039-13075.
An additional approach not included in Table 1 is the work of Aktar et al. in using deep learning to detect DDOS attacks.
Aktar, Sharmin, and Abdullah Yasin Nur. "Towards DDoS attack detection using deep learning approach." Computers & Security 129 (2023): 103251.
Finally, while the paper below does not provide a machine learning or deep learning approach to DDOS detection it does describe how potential DDOS threats can be generated using MCMC and then identified and pro-actively protected against. Including this study as an additional means of motivation would improve the paper.
Gore, Ross, Jose Padilla, and Saikou Diallo. "Markov chain modeling of cyber threats." The Journal of Defense Modeling and Simulation 14.3 (2017): 233-244.
Strengths:
The article contains original primary research that is within the scope of the journal.
The research question is well defined, relevant and meaningful.
The investigation is performed to a high and rigorous ethical standard.
Weaknesses
There are a number of references itemized above and below here that would help motivate and facilitate reader understanding about how the research fills an identified gap.
In order to truly describe the methods in detail with sufficient information to replicate the source code used to produce figures 2-7 should be shared.
The paper would be improved by performing a statistical comparison to show the proposed approach is statistically significantly more accurate than the other alternatives. As it is presented now it is clear that the proposed approach is the most accurate but without a test for statistical significance it is unclear if the evaluation shows that the proposed approach is materially better than the alternatives. By addressing this weakness the paper will rigorously perform investigation to a high technical standard.
Strengths:
The impact and novelty of the proposed work are assessed. There is meaningful replication in the evaluation and the rationale & benefit to literature is clearly stated.
The data and source code for the evaluation and algorithm are provided.
Weaknesses
In order to truly provide all data the source code used to produce figures 2-7 should be shared.
In order to have robust, statistically sound, and controlled experimentation a statistical comparison to show the proposed approach is statistically significantly more accurate than the other alternatives should be performed. Doing this would better link the research question to the results providing more valid conclusions.
The paper is written in clear and unambiguous professional English. The literature references and citations are adequately provided. The table, figure, and raw data are shared and formatted correctly. The results are self-explained and all the definitions. terms and theorems are clearly mentioned.
The paper is within the Aims and Scope of the journal, the research question is clearly defined, relevant, and meaningful. The authors performed rigorous investigations and maintained high technical and ethical standards. Most of the provided information is sufficient for the reproducibility of the paper.
The findings of the research are weak as the author solely relied on the one metric of evaluation. Accuracy could be a weak measure of performance for the class-imbalanced classification problem ( where one class has an overwhelmingly higher prevalence over other minority classes) and cyber-attack comes under such categories where an anomalous signal has very concentration over the benign signal. F1 Score, AUC could have been used to evaluate. The author could have also performed major statistical tests to further support the findings. Overall, the paper needs some more statistical pieces of evidence before it can be accepted for robust submission.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.