I am a computer scientist specialising in Artificial Intelligence Security. I held postdoctoral research roles at Oxford, Cambridge, ICL, and MIT.
-
University of Oxford
- Oxford, England
- https://www.cs.ox.ac.uk/people/petar.radanliev/
- https://orcid.org/0000-0001-5629-6857
- https://scholar.google.com/citations?user=zx0_aTwAAAAJ&hl=en
- https://orcid.org/0000-0001-5629-6857
- @AISecurityOxford
- https://www.turing.ac.uk/people/research-associates/petar-radanliev
Popular repositories Loading
-
Agentic-AI-Security-Demos
Agentic-AI-Security-Demos Public archiveAgentic AI security bootcamp: labs for multi-agent observability, prompt injection, LPCI, red-teaming, adversarial evaluation — hands-on training.
-
Red-Teaming-Multi-Agent-AI-Systems-
Red-Teaming-Multi-Agent-AI-Systems- Public archiveRed Teaming Multi-Agent AI Systems - Learn how to simulate, test, and defend against coordinated cyber-attacks on autonomous agent networks.
-
AI-Attack-Surface-The-10-Most-Critical-Threats-to-ML-and-AI-Systems
AI-Attack-Surface-The-10-Most-Critical-Threats-to-ML-and-AI-Systems Public archiveThis live course, “AI Attack Surface: The 10 Most Critical Threats to ML and AI Systems”, offers practical, step-by-step guidance to identify, analyze, and mitigate AI-specific attack vectors.
-
-
Red-Teaming-Multi-Agent-AI-Systems
Red-Teaming-Multi-Agent-AI-Systems Public archiveAgentic AI Security Bootcamp: Week 4
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.

