Memuat
Memuat
Want to go deeper?
Join one of our courses or ask us directly on WhatsApp.
Picked from the software, topic, and level of “Class Hybrid ML Intrusion Detection Network IoT #6: Detection Evaluation, False Alarms, and Monitoring Dashboard”.
Other ways we can help with Python.
Learn with a mentor
Scheduled Cyber Security courses with live guidance and a certificate.

IoT Network Intrusion Detection Course with Hybrid Autoencoder + XGBoost

Cyber Security Course: Foundations of System & Network Security

Ethical Hacking Course: Web Application Penetration Testing
Have it built for you
No time to learn Python? Our team can do the project for you.
See all in Cyber Security →Get notified about new Python classes
At most one email a week. Unfollow anytime with one click.
The full narration of this video. The current sentence is highlighted while the video plays; click any sentence to jump there.
This is the final result, our intrusion detection system monitoring dashboard. Traffic is streamed per 500 connections window, alarms and attack categories are monitored, the service most frequently attacked is visible, and its performance summary appears like in the Security Operations Center. Let's start. Hello, welcome to the final episode of the IoT Network Intrusion Detection series with Hybrid Machine Learning. An accurate model is not enough, security operators need actionable information. Today we evaluate the Hybrid system in detail and build a monitoring dashboard like in the Security Operations Center.
Create dashboard.py file We load XGBoost, AutoEncoder, and threshold from the Hybrid configuration file. The detection function runs the Hybrid pipeline for one traffic window, so it can be used for data streams gradually. Then we evaluate all the test data. Run The Hybrid system detects 86.7 percent of attacks with 10.6 percent false alarms. Per category, The OS is detected at 97 percent, Probe at 99.9 percent, U2R at 92 percent, and R2L at 47 percent, the hardest category because its attacks resemble normal login. There are 3,460 new anomaly alarms, and 78.4 percent of them are actual attacks, proof that the AutoEncoder layer is very useful.
Proceed to the dashboard. Test traffic is ordered as real flow, Then divided per window 500 connections. The dashboard has 4 panels, number of alarms per window, composition of alarms per category, services that are most frequently attacked, and summary KPI. Let's look at the dashboard. The alarm graph shows 240 to 290 alarms per window, sudden spikes indicate large attacks that need to be followed up on. The composition shows The OS dominates, followed by new anomalies in purple. Private services, telnet, and eik TTP are most frequently attacked, indicating which configurations need to be tightened.
Done, and the series is also finished. We have built a complete intrusion detection system, dataset and types of attacks, preprocessing, feature selection, random forest, XGBoost, autoencoder, hybrid system, until evaluation and monitoring dashboard. For further research, try modern IoT datasets like CIC IoT 2023, real-time detection from packet captures, federated learning across devices, or explainable AI to explain every alarm. Thank you for following this series. Working on a thesis, dissertation, or research in the field of network security and machine learning? Cerdas Inovasi Digital helps implement intrusion detection systems, from network traffic preprocessing, feature selection, random forest and XGBoost, up to autoencoder for 0DI attacks and monitoring dashboard, as well as opening Python programming courses for electrical engineering and computer science. Want to master the entire series? From intrusion datasets to hybrid systems ready for monitoring? All 6 episodes, complete with step-by-step PDF guides, datasets, and source code, are available for premium tutorial subscribers. Subscribe starting at Rp69.000 per month, save 28% with the 12-month package, or pay once Rp999.000 for lifetime access. Want a single class only? Buy single classes with lifetime access. Subscribe now at the premium page cerdasinovasidigital.com Contact us via WhatsApp, or visit cerdasinovasidigital.com Thank you for watching, See you in the next episode. Thank you for watching,
Type a question or keyword; we find the part of this episode that explains it and jump the video there.
Notes are saved with the current video time and are only visible to you.
Stuck on a step? Ask here; the instructor and other learners can answer.
No questions yet.

Cerdas Inovasi Digital Team
Software developers, BIM & 3D engineers, and AI practitioners
We build software, BIM models, games and AI automations for clients every day, and turn that hands-on work into step-by-step classes: every step is shown on screen and comes with a PDF guide you can keep.
See our clients →