- Engineer — Learn: If you’re deploying RAG pipelines, this research shows that defenses evaluated purely on attack success rate can still introduce unexpected target-positive outputs — worth reviewing your evaluation framework before trusting any poisoning defense you’ve implemented.
- SOC/IR — Skip
- Leader — Learn: Useful context for AI governance discussions: defenses on enterprise RAG systems may have overstated efficacy, which matters when briefing on AI risk posture or assessing vendor claims about RAG security controls.