Understanding the Influence of AST-JS for Improving Malicious Webpage Detection
, Seiichi Ozawa 2,3, Tao Ban 1, Sangwook Kim 2, Takeshi Takahashi 1 and Daisuke Inoue 1
Round 1
Reviewer 1 Report
The article titled “Understanding the Influence of AST-JS for Improving Malicious Webpage Detection” propose a new webpage feature extraction program, i.e., AST-JS, that recognizes the semantic meaning of the JS code embedded in HTML content. The work done is very interesting and timely. Still, I am sceptical about the practicality of the proposed approach since the demands of real-time scenarios could only be met by lightweight approaches.
I want the authors to address the above-mentioned concern and the comments in the revised manuscript.
-
The paper's motivation needs improvement, for example, by adding some statistics/references in the introduction section to show Javascript's importance as a leader in the client-side application programming language.
-
A table should be added to summarize the findings of the related works section.
-
The two examples of malicious web pages must be improved. For example, a separate figure for phishing webpage be added with two sub-figures (one for legitimate websites and the other for phishing websites). Figure 1b can be improved on similar lines.
-
Reference missing “SHAP” line 283 or even for the first time it is discussed.
-
Section 4.1 - what makes the selected dataset complicated? Also, discuss the inclusion/ exclusion criteria of the data set.
-
Why other datasets are not considered for training and testing purposes?
-
The representation of results in Figures 6,7, and 10 should be improved.
-
I do not find any discussion on the application of the proposed approach. How the proposed approach can be adopted by web browsers? For example, the authors can provide it as a plug-in for web browsers. If so, what about the real-time performance of this approach?
-
Overall, the paper is well written.
Author Response
Thank you very much for your comments.
Please see the attachment. We try to answer your point-by-point to your comments.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Please find the attached file
Comments for author File: Comments.pdf
Author Response
Thank you for your comments.
Please see the attachment to see our answer to your comments.
Author Response File: 
Author Response.docx
Round 2
Reviewer 1 Report
I am satisfied with the author's response.
