Sponsored Keynote: Lessons Learned in LLM Prompt Security - Jakub Suchy
Jakub Suchy
KubeCon + CloudNativeCon Europe 2025 · Sponsored Keynote
In this insightful keynote at KubeCon EU, Jakub Suchy from Haroxy Technologies delved into the critical, yet nascent, field of **Large Language Model (LLM) prompt security**. Drawing a stark parallel to the early days of web security, specifically the "2003 of OWASP Top 10," Suchy underscored the urgent need for robust security measures as organizations rapidly adopt AI. The talk highlighted a significant gap in current AI gateway implementations: while they often cover authentication, rate limiting, and PII detection, **prompt security** is frequently overlooked or inadequately addressed.
AI review
This sponsored keynote from Haroxy Technologies delivers a brutally honest, data-driven assessment of LLM prompt security in AI gateways. Jakub Suchy presents empirical evidence demonstrating the severe performance bottlenecks introduced by current LLM-based classification models like Llama Guard and Shield Gemma. While it doesn't reveal a zero-day, it provides critical, actionable intelligence for architects and security professionals, challenging the naive assumption that AI can secure AI without significant engineering and performance overhead. It's a refreshing deviation from typical…