Breaking Models đ¨AI Security
Sessions
- 2:30 PM â 4 PMSource â
- 3 PM â 4:30 PMSource â
About
Breaking Modelsđ¨ Session 5: Leak & Build Edition Part 1 - LLM02: Sensitive Information Disclosure The stuff AI apps leak: API keys, customer records, system prompts, other peopleâs conversations. This category sat at #6 on the original OWASP Top 10 for LLMs. In the 2026 update it jumped to #2, right behind prompt injection, and it holds that spot in 2026. Weâll 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 isnât. Together weâll 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! đŠ RSVP (or to present at a future session): aisecurityinbay@proton.me đ 9 August ¡ 2:30pm - 4:30pm đ Hacker Dojo, Mountain View
