Causal AI DDoS

Started in February 2024

Causal AI is a promising new technology. Drawing conclusions based on correlations alone can be misleading. Therefore, we are interested in methods to find the invariant causal relationships. In fact, causal AI aims to identify causes and effects.

https://pcsi.nl/uploads/projects/Causal-AI-DDos-b.png

Project proposal

In our exploration and further understanding of causal AI, we focus on the Layer 7 (L7) DDoS use case. Countering L7 DDoS attacks and their preparation requires a different approach than mitigating volumetric DDoS. The project builds on the knowledge gained from the previous PCSI project "Crystal Ball DDoS Detection".

Expected gains of the Causal AI DDoS project?

Proactive threat detection
Enhanced defense
Improved decision-making
Universal application
Business continuity

Why do we want to work on this idea within the PCSI?

Collaborate on the same challenges
Innovate together

Our use-case: Layer 7 DDoS attacks.

Detects anomalies & their root causes
Alerts with reasons, not just flags
More accurate detection

Activities in Explore phase

Explore causal AI
Discover causal relations in public data sets for Layer 7 DDOS attacks
Define use cases

The fictional image above is created with the use of DALL-E

This project is part of the trend

21 Opportunity June 2025

Transition to predictive technologies

In the past, security defences were built around preventive measures. This was complemented with monitoring & response, to be able to detect attacks that circumvented preventive measures. But the gap between attackers' odds and defenders' strategy is still growing. That is why we also have to make use of predictive technologies (based on deep or reinforcement learning algorithms) to be able to better prepare for sophisticated attacks, and to support predictive or 'smart' decision making in cybersecurity or proactive risk management regarding cyberthreats.