Detection of Adversarial DDoS Attacks Using Symmetric Defense Generative Adversarial Networks

Round 1

Reviewer 1 Report

This work examines DDoS attack detection using GAN. The proposed work is validated by comparison with state-of-the-art techniques using publically available datasets. The hyperparameter selection and training are provided. 

Some suggestions are as follows:

1- The introduction part can be improved by adding more recent work related to DDoS detection

2- The study's contribution can be improved by discussing more specifically the gaps in previous works being addressed in this paper.

3- Some minor English editing is needed, e.g., in the introduction, "demonstrates its potential in various filed..."

4- In the abstract, TPR is used without a prior definition of the acronym.

5- Section 4.2 has the following immediate subsection; some lines may be added to keep the flow continued.

Author Response

Thank you for your time and effort in reviewing our manuscript. We deeply appreciate the invaluable and instructive comments from the reviewer, based on which we can further improve the quality of this work. Please see the attachment for detailed responses.

Author Response File: Author Response.docx

Reviewer 2 Report

The presented paper proposes a novel framework for detecting adversarial DDoS attacks, entitled Symmetric Defense Generative Adversarial Network (SDGAN). The article is structured into 3 main sections. In the second section, the authors present an overview of related topics, namely, the utilisation of artificial intelligence for DDoS Detection, the Generative Adversarial Networks, and the Adversarial DDoS Attack. The proposed approach in the third section introduced the CycleGAN and SDGAN models with appropriate training algorithms. The results suggest that the proposed SDGAN architecture is an effective approach to battle the adversarial DDoS attacks (in comparison to machine learning-based DDoS detectors). The paper is well written and the overall structure and methodological soundness are on a good level. 

Author Response

Thank you for your time and effort in reviewing our manuscript. We deeply appreciate the approval from the reviewer. Please see the attachment for our response letter.

Author Response File: Author Response.docx

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.