TTPSEC AI
$ R&D on artificial intelligence applied to cybersecurity.
TTPSEC AI is the group's R&D lab focused on the intersection of artificial intelligence and cybersecurity. Two fronts: how AI changes the tempo of offensive and defensive operations, and how AI itself is attacked once exposed in production.
This is where the OVNI-Agentic HoneyPot Net comes from — sensors that emulate LLM endpoints (ollama, OpenAI, Claude, DeepSeek) to capture, live, the reconnaissance, jailbreak attempts and targeted exploitation aimed at exposed models. The resulting dataset is public and openly licensed.
The research does not stop at the paper: it feeds the consulting methodologies, the academy scenarios and the labs tooling. This is applied R&D, not speculation.
// what it offers
- 01
> LLM security
Analysis of prompt-injection, jailbreak and abuse of models exposed in production.
- 02
> Offensive and defensive AI
Study of LLM agents in pentesting, red team and assisted detection.
- 03
> Agentic honeypot
Sensors capturing real attacks against AI endpoints, with an open dataset.
- 04
> Applied research
Findings transferred straight into services, training and tooling.