Now 27 visitors
Today:159 Yesterday:1040
Total: 27944 199S 93P 40R
2024-11-27, Week 48
Journal Homepage
Call for Paper
Author HomePage
Paper Procedure
Paper Submission
Registration Invoice
Welcome Message
Statistics & History
Committee
Paper Archives
Outstanding Papers
Conference Proceedings
Presentation Assistant
Hotel & Travel Info
Photo Gallery
FAQ
Member Login
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)
ICACT20220314 Question.1
Questioner: lchen@mail.ntust.edu.tw    2022-02-15 ¿ÀÀü 7:20:02
ICACT20220314 Answer.1
Answer by Auhor nay.min@student.mahidol.ac.th   2022-02-15 ¿ÀÀü 7:20:02
Chrome Click!!
Thank you for your analysis and discussion of this Top 10 based Attack Dataset for the Machine Learning method. Do you have any suggestions for future applications with your way? We intend our dataset to be used in training small and medium network environment security systems. For our case, we are currently using this proposed dataset to classify the benign and anomaly traffic for our security system where we will integrate with software-defined network technology.
ICACT20220314 Question.2
Questioner: tomayoon@ieee.org    2022-02-15 ¿ÀÀü 7:26:50
ICACT20220314 Answer.2
Answer by Auhor nay.min@student.mahidol.ac.th   2022-02-15 ¿ÀÀü 7:26:50
Chrome Click!!
First of all, thank you for the good research paper and presentation contents. I would like to know more about the research environment used in this study, and also in detail about the equipment & operating systems, development languages and software libraries you used. Thank you for your compliment and your question. We have provided our detailed environment in our paper under chapter III. AIoT-Sol Testbed Design. We mentioned the specifications of both the physical devices (hardware, software, os) and the virtual machines with a comprehensive table.
ICACT20220314 Question.3
Questioner: nishat.mowla@ri.se    2022-02-17 ¿ÀÀü 1:39:25
ICACT20220314 Answer.3
Answer by Auhor nay.min@student.mahidol.ac.th   2022-02-17 ¿ÀÀü 1:39:25
Chrome Click!!
Most datasets considered for use with machine learning have a common problem of being noisy and imbalanced. Have you considered that during your attack generation or any technique considered after the attack generation? Thank you for your discussion and question. We also noted that these common problems exist even in our testbed. However, we tried our best to address these issues although they are not perfectly solved yet. For the imbalance case, we control the number of durations that our attack is performed and fix the total number of times we perform for each category. For the noise issue, we had to filter using specific protocols using wireshark filters.
ICACT20220314 Question.4
Questioner: namacabale@gmail.com    2022-02-15 ¿ÀÈÄ 6:49:01
ICACT20220314 Answer.4
Answer by Auhor nay.min@student.mahidol.ac.th   2022-02-15 ¿ÀÈÄ 6:49:01
Chrome Click!!
Dear Author, you have a very good research. Is there an existing technology almost similar to your proposal that has been deployed in real world environment? What does it lack that your work specifically addressed? Thank you and stay safe. Thank you for your question. Our current paper doesn't include the security system yet; instead, we share our dataset that will be used for such a system in our further research. We have seen several network security systems that utilize machine learning technology based on several datasets for various purposes. As for the dataset with a real-world environment, I think the ones in the following link are very famous. https://www.unb.ca/cic/datasets/
ICACT20220314 Question.5
Questioner: lusongfeng@hust.edu.cn    2022-02-15 ¿ÀÈÄ 6:53:15
ICACT20220314 Answer.5
Answer by Auhor nay.min@student.mahidol.ac.th   2022-02-15 ¿ÀÈÄ 6:53:15
Chrome Click!!
Dear author, thank you for your presentation. I want to ask you a question about Are there any machine learning method or cryptography tools to resist the attack dataset work in IoT field? Thank you for your interesting question. To my best knowledge, the use of the machine learning method can be limitless at this moment with only a need for a sufficient dataset. Therefore, I would say, no system nor technology is safe since it is only a matter of time and the computing power that requires to crack a security solution. However, there must be several kinds of research attempting to resist such attacks for as long as possible.
ICACT20220314 Question.6
Questioner: songpon.tee@mahidol.edu    2022-02-17 ¿ÀÀü 1:00:59
ICACT20220314 Answer.6
Answer by Auhor nay.min@student.mahidol.ac.th   2022-02-17 ¿ÀÀü 1:00:59
Chrome Click!!
Thank you for your presentation. Just curious, since SSH brute-force attack was included in many previous dataset, why did you decide not to include it in your dataset? Hello, thank you for asking. SSH brute-force is not omitted in our dataset as well. Actually, it went under Network Logon Bruteforce Subcategory. We attacked multiple protocols such as SSH and Telent.
ICACT20220314 Question.7
Questioner: ycc.nttu@gmail.com    2022-02-17 ¿ÀÀü 12:30:46
ICACT20220314 Answer.7
Answer by Auhor nay.min@student.mahidol.ac.th   2022-02-17 ¿ÀÀü 12:30:46
Chrome Click!!
Thank you for your analysis and discussion of this new AIoT-Sol dataset for anomalous activity detections in IoT networks. Would you please let us know how to select 17 relevant attack types to produce a comprehensive dataset? Thank you for your interest in our dataset. Initially, we prioritize having a dataset with benign and anomaly traffic. And then we categorize them into a category class: Network, DDoS, Web, Web IoT Message Protocol Attacks. As for the 17 attack types, we tried to decide under the four categories. After considering the constraints of testbed and attack types, we came up with possible attack types that we can perform. However, a comprehensive dataset is not limited to 17 attack types only.