Breaking Models 🚨AI Security

Breaking Models🚨 Session 5: Leak & Build Edition

Part 1 - LLM02: Sensitive Information Disclosure

The stuff AI apps leak: API keys, customer records, system prompts, other people’s conversations. This category sat at #6 on the original OWASP Top 10 for LL

Ms. In the 2026 update it jumped to #2, right behind prompt injection, and it holds that spot in 2026. We’ll walk through how these leaks actually happen. Most of them need no jailbreak, just normal usage, and what actually stops them.

Part 2 : Design exercise: build a secure agentic system

Something new this session. Instead of only talking about broken systems, we design one that isn’t. Together we’ll threat model an agentic AI app, where it can leak, where it can be hijacked - and then sketch a secure architecture for it. You do the practical design, not just the listening.

Talk first, then the exercise, then open floor. No vendor pitches. Beginners welcome!

📩 RSVP (or to present at a future session): aisecurityinbay@proton.