Scribd
Upload
1 views

jarkom scripts

The journal discusses the application of Machine Learning (ML) in computer networks, highlighting its role in enhancing security and efficiency by detecting threats like SQL Injection and DDoS attacks. It outlines research methods including literature reviews and case studies, and emphasizes the use of hybrid ML models for improved detection accuracy. The conclusion points to future directions such as Federated Learning and 5G integration to further enhance data security and system responsiveness.

Uploaded by

yasifayasifa309
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
1 views

jarkom scripts

The journal discusses the application of Machine Learning (ML) in computer networks, highlighting its role in enhancing security and efficiency by detecting threats like SQL Injection and DDoS attacks. It outlines research methods including literature reviews and case studies, and emphasizes the use of hybrid ML models for improved detection accuracy. The conclusion points to future directions such as Federated Learning and 5G integration to further enhance data security and system responsiveness.

Uploaded by

yasifayasifa309
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

1.

assalamualaikum warahmatullahi wabarakatuh, I am a representative of group 5 consisting of kilala mahadewi,


auliya rohman, ahmad munfarid, syahrul ibnu, and I am yasyifa nur bani. I will explain the journal that we have
made with the title: Application of Computer Networks in Machine Learning.

Today, almost every aspect of our lives relies on technology and computer networks, from communication, financial
transactions, to data security.
Machine Learning (ML) helps computers recognize patterns from huge amounts of data, allowing them to make
decisions without having to be programmed directly.
When ML is applied to computer networks, we can get smarter systems in detecting security threats and increasing
efficiency in various industries.

2. Increasingly Sophisticated Threats: Attacks like SQL Injection and DDoS can lead to data leaks or make systems
inaccessible.

Solutions with ML:

ML can learn from previous attack patterns to recognize and block new ones.

Systems can respond to threats automatically, without the need for direct human intervention.

Simple Example:

Imagine a home security system that can distinguish between a regular guest and a suspicious person based on
movement patterns and facial expressions. This system is similar to how ML works to detect attacks on computer
networks.

3. the research method by using: the first Literature Review: Collecting and analyzing the latest research from various
scientific sources such as ScienceDirect, Scopus, and ACM Digital Library (between two thousand twenty and two
thousand twenty four).
then the second Case Study: Testing how ML can detect attacks such as SQL Injection and DDoS.
and the last ML Workflow: Developing step-by-step stages to apply ML in computer networks.

4. DDoS Detection with Hybrid ML Models has Improved Accuracy and Network Advantage.
The solution with ML is to use a combination of two techniques (Naïve Bayes and Random Forest) to improve
detection accuracy.
As a result, the system can distinguish between normal traffic and attacks with almost one hundred percent
accuracy
Then a Better Distributed Network because, the system can learn from various data sources around the world, so it
can recognize new attack patterns faster.

5. SQL Injection Vulnerability Scanning


ML Can Help by Using OWASP ZAP to find twenty-two vulnerabilities in web applications, three of which are high
risk, and Showing that using the HTTPS protocol can reduce vulnerabilities by fifty percent.
But there is a challenge, ML still has difficulty detecting new attacks , so it needs continuous training and updates.

6. Risk Management in Industry (four zero points) there are Collaborative Framework, Anomaly Monitoring, and
Federated Learning.
ML helps detect Anomalies If there is unusual sensor data, the system can give alerts faster.
then in Federated Learning, ML Models can learn from many data sources without having to collect all the data in
one place, making it safer and more privacy-preserving.
The advantage is that response time to threats can be accelerated by up to (sixty five percent).

7. then there is Cross-Study Analysis including scalability, adaptation, and accuracy.


on scalability, ML Models can handle large amounts of data without interruption.
then on adaptation, Models can be automatically updated to face new threats.
the last on accuracy, Data preprocessing techniques can reduce detection errors by up to fifty percent

8. In conclusion, Enhanced Threat Detection with ML helps detect attacks faster and more accurately. then, Proactive
Vulnerability Mitigation is where the System can identify and fix weaknesses before they are exploited.
and finally Resilient Industry Framework with the combination of computer networks and ML creates a more robust
system in the face of modern threats.

9. Next, the Future Direction or what technology is being developed, namely: there is Federated Learning, by
Increasing data security by training ML models without collecting data in one place. Next, 5G Integration, by
Leveraging high speed and low latency to support real-time ML applications. Finally, Human-in-the-Loop Systems,
by Combining ML intelligence with human expertise to make the system more accurate and not completely
dependent on machines.

That's all the journal presentations from group five, wassalmualaikum warahmatullahi wabarakatuh

You might also like