Andrés Murillo

MIRROR outperforms traditional red-teaming methods, achieving a staggering 97% attack success rate on orchestrator-level attacks while maintaining efficiency and novelty constraints.

AI sandboxes can be rigorously defined to expose vulnerabilities in assurance mechanisms, revealing what risks they can truly contain.

Stateful defenses are not just better, but *necessary* to protect multimodal RAG agents from sophisticated attacks that bypass stateless filters.