We Red-Teamed Open-Source LLMs. Then We Built Citadel.
Prompt-injection risk is more than just text. It includes images, documents, and tool calls etc. We need invisible APIs that keep everyone safe in production, especially open-source models.
Mighty
The Mighty blog delivers expert thought leadership on secure AI and data privacy, timely product release updates, and in-depth spotlights on our partners’ innovations.
Live Last read · last published · next check