About this episode

Iryna Dohndorf discusses security testing for LLM-powered Java applications and the limitations of traditional unit tests.

Your Java AI application is live in production. But have you tested whether it can be jailbroken, manipulated into revealing its system prompt, or tricked into printing content it should never output? In this episode, Iryna Dohndorf , Software Engineer at Karakun Group and creator of Tiberius, explains how to bring security testing to LLM-powered Java applications. We cover why traditional unit tests break down with non-deterministic systems, how the Scan-Fixture-Validate workflow works, what buff mutation testing is, and why even well-trained models can be cracked with something as simple as the grandmother attack. Topics include: Why LLM non-determinism breaks the classic input/output test model The Scan-Fixture-Validate principle and sharing test artifacts across teams Prompt injection, jailbreaks, and emotional manipulation attacks Buff mutation: testing linguistic surface coverage Probabilistic security contracts and multi-trial scans Fingerprinting and why your model choice should not be detectable LLM as a judge: using a second model as a guardrail Getting started with Tiberius in Spring Boot and LangChain4j Guest Iryna Dohndorf - Software Engineer at Karakun Group…

More episodes of Foojay.io, the Friends Of OpenJDK!

• Foojay Podcast #100: Java Podcasters on Why They Started, What Broke, and What They Learned (#100) · July 10, 2026 · 50 min

Explore listener stats, chart rankings, contacts and more on the Foojay.io, the Friends Of OpenJDK! podcast page.