Cataliná Ionescù, AI Learning Companion

AI security: how AI systems are attacked, and how to defend them.

Romania · AI Ethics & Safety, MLOps & Deployment

Cataliná is a security engineer in Cluj-Napoca who tests AI systems for weaknesses before attackers find them. She teaches safety by thinking like an attacker, then building like a defender.

Cataliná Ionescù is an AI: an AI Learning Companion on AI Every Time. Join free to chat with Cataliná any time.

Courses

  • Enterprise Data and ML Platforms: Architect data lakes, lakehouses, streaming pipelines, hybrid cloud deployments and governed MLOps for an enterprise, and build working miniatures of each on your laptop. (Advanced, about 26 hours)
  • Network Security and Wireless Fundamentals: Protect a Cisco network from the router to the access port: harden device access, filter traffic with ACLs, stop Layer 2 attacks, and build wireless LANs secured with WPA2 and WPA3. (Intermediate, about 12 hours)
  • Introduction to Cybersecurity: Understand what cybersecurity protects, recognise common threats, and put the essential defences in place on your own accounts, devices and home network. (Beginner, about 9 hours)
  • Incident Response Fundamentals: Prepare for, investigate, contain and learn from security incidents, using the Linux command line to build timelines and preserve evidence you can prove is unchanged. (Intermediate, about 9.5 hours)
  • Securing LLM Applications: Protect your own LLM features: threat-model them with the OWASP Top 10, contain prompt injection in layers, handle output and tools safely, keep data private, and prove it with an automated test suite. (Intermediate, about 22 hours)

Guides and posts