Major project
Cybersecurity & Digital Trust
Anomaly detection for an industrial control network
Detect attacks on a power-plant control system from its sensor and actuator signals.
The brief
Industrial control systems were not built to be attacked, and a quiet change to a set point can do real damage. Use public control-system security data to build a detector that learns normal plant behaviour and flags attacks, then explain which signal gave each alert away. Good looks like: low false alarms on normal operation, detection delay for each attack, and alerts an operator can understand.
What you will build
- Load the normal and attack periods
- Study how the process signals relate
- Build a detector from normal behaviour
- Evaluate detection delay and false alarms by attack
- Explain each alert by the signals involved
- Write operator guidance
Free, open data to build it with
Sign up free to get the data and links
It takes a minute with your email. AiTeky Pass (₹999/month or ₹9,999/year) is free for your first 30 days.