Now 718 visitors
Today:392 Yesterday:362
Total: 2834 413S 88P 97R
2026-04-13, Week 16
Member Login
Welcome Message
Statistics & History
Committee
TACT Journal Homepage
Call for Paper
Paper Submission
Find My Paper
Author Homepage
Paper Procedure
FAQ
Registration & Invoice
Paper Archives
Outstanding Papers
Program & Proceedings
Presentation Platform
Hotel & Travel Info
Photo Gallery
Scheduler Login
Seminar
Archives Login
Sponsors




















Paper Number Author:
Paper Title
Keyword
Q&A Number **Select your question number !!
Questioner eMail:
Question
Answer
by
Author
Save Q&A

* Edit or answer any Q&A by selecting Q&A number Hyper Link below + Write button (Save)
ICACT20230048 Question.1
Questioner: 6025211020@mhs.its.ac.id    2023-02-22 ¿ÀÈÄ 12:14:51
ICACT20230048 Answer.1
Answer by Auhor lchen@mail.ntust.edu.tw   2023-02-22 ¿ÀÈÄ 12:14:51
Chrome Click!!
Interesting research. In log data stored in dataframe format, there are several features such as Timestamp, Session_Timestamp, src_port, ip, and payload. Which features are included in the clustering process? and why were these features chosen? Is including all the features the most effective and efficient way to build a K-Means Clustering model? Thank You. Thank you for your question. We only use Payload as the Feature of the Cluster. The K-means algorithm is only used by us as a Cluster for classifying Payload so that it can be used as a marking tool later. Hope to answer your question, Best Regards.
ICACT20230048 Question.2
Questioner: m11007505@mail.ntust.edu.tw    2023-02-22 ¿ÀÈÄ 12:07:36
ICACT20230048 Answer.2
Answer by Auhor lchen@mail.ntust.edu.tw   2023-02-22 ¿ÀÈÄ 12:07:36
Chrome Click!!
Thank you for your presentation. I noticed that this research uses k-means algorithm to classify attack payloads. Why did you decide to use k-means instead of other classification algorithms and how do you decide your k value here? Best regards. Thank you for your question. We have tried many algorithms, such as DBScan, and finally, K-means is the most suitable for our desired effect. We set the k value to 31 and decided on k value via the WCSS algorithm. Best regards.
ICACT20230048 Question.3
Questioner: ali.athar1401@gmail.com    2023-02-22 ¿ÀÈÄ 12:39:42
ICACT20230048 Answer.3
Answer by Auhor lchen@mail.ntust.edu.tw   2023-02-22 ¿ÀÈÄ 12:39:42
Chrome Click!!
Hello, Thank you for presenting this paper. Can you tell us more about the limitation of your research and your future plans to enhance your research work? Thank you. Thank you for your question. Because our Honeypot does not have important information like a real computer, many Payloads are only accessed, and there is no follow-up action. Therefore, the more threatening Payloads account for a small part and may be installed in the future. Other kinds of Honeypots can do the same analysis as cloth. Thank you. Best Regards.
ICACT20230048 Question.6
Questioner: h22001iy@edu.tuis.ac.jp    2023-02-20 ¿ÀÈÄ 2:54:04
ICACT20230048 Answer.6
Answer by Auhor lchen@mail.ntust.edu.tw   2023-02-20 ¿ÀÈÄ 2:54:04
Chrome Click!!
Thank you for your presentation. In this study, did you operate a honeypot, or did you obtain a dataset from a honeypot provider? Additionally, if you did operate a honeypot, could you please share any measures you took to attract attacks? Best regards, Hi, thank you for asking this question! Our dataset is obtained from the honeypot provider for subsequent analysis and research. In addition, our honeypot uses cowrie honeypot. Hope this answer helps you!