# Tim Vignon — Portfolio

> Systems you can trust. Agents you can watch. Final-year engineering student at UTT (Troyes, France) in networks, cybersecurity and AI, focused on runtime security for AI agents. Portfolio with an interactive 3D globe; available in English, French, Chinese and Korean.

Site: https://timvignon.fr
Full content for AI readers: https://timvignon.fr/llms-full.txt

## Pages

- [/](https://timvignon.fr/): Home: headline, current focus, three selected projects
- [/work](https://timvignon.fr/work): Work: all projects pinned to a 3D globe
- [/about](https://timvignon.fr/about): About: bio, work experience, hackathons & CTF, education, skills
- [/contact](https://timvignon.fr/contact): Contact form, email, CV download
- [CV (PDF)](https://timvignon.fr/cv/Tim-Vignon-CV.pdf)

## Projects

- mcp-watch: Runtime Security for AI Agents (AI Agent Security, 2026, Pre-alpha): Open-source runtime sensor for MCP-based dev agents: a transparent proxy that baselines tool-call behaviour (Isolation Forest) and scans received messages for indirect prompt injection, correlating both into alerts. Master’s thesis artifact, 150+ tests, live demo.
- Praetor: Physics-Informed Predictive Maintenance (AI Agents × Industry, 2026, Hackathon prototype): Living digital twin predicting industrial machine failures days ahead with no extra hardware: Physics-Informed Neural Networks embed each machine’s equations and infer its state at uninstrumented points. An accountable agent chain (HMAC-signed readings, citable digests, defence/attack/judge agents, LLM jury) vets every alert. Built in 24 hours with a team of five, where I owned the full-stack app and the agentic AI layer. 2nd place at RAISE Summit Hackathon 2026.
- D-Valentin: VC Intelligence Platform (Product Engineering, 2026, Ongoing): Evidence-first platform analysing startups and founders through a traceable proof chain (sources → evidence → claims → auditable reports), with pitch-deck analysis, RAG chat and multilingual memos. Frontend owner in a three-developer team.
- Multi-Camera AI Surveillance (LIST3N Research) (Computer Vision Research, 2026): Six-month research internship at the LIST3N lab: real-time industrial safety detection with YOLO and ByteTrack on synchronized camera streams, a Bird’s Eye View fusion pipeline projecting detections onto a floor plan via homography, and an edge-versus-cloud benchmark of YOLOv8/11 and RT-DETR.
- DLP Network: Data Exfiltration Detection (Cybersecurity, 2025, In Progress): Open-source network DLP analyzing real-time flow metadata (NetFlow/IPFIX) to detect and block data exfiltration with graduated response.
- Speak My Notes (AI Product, 2026, Prototype): Mobile-first prototype turning photographed language-class notes (Chinese, Korean, French) into immediate speaking practice: vision extraction with the Claude API and a local-first learner memory.
- Freelance Web Development for Local Businesses (Web Development, 2025, Ongoing): Bespoke showcase websites for small businesses across Burgundy, with end-to-end ownership from prospecting and UI/UX design to deployment and client management.

## Current focus

Agents cannot reliably tell instructions from data. A hidden instruction in a document or a tool response can hijack them while they hold legitimate credentials. My master’s research targets indirect prompt injection on the Model Context Protocol, and mcp-watch is its open-source counterpart. Live demo: https://mcp-watch-demo.fly.dev/

## Contact

- Email: tim.vignon@gmail.com
- GitHub: https://github.com/frisatim
- LinkedIn: https://www.linkedin.com/in/tim-vignon-110701260
- Location: Vitteaux / Troyes, France