title: "AI is its own best safeguard: Glean uses AI to detect jailbreak attempts at 97.8% accuracy"

Glean is pioneering a new method of AI security by using AI itself to safeguard against malicious attacks. These attacks, known as jailbreak attempts, involve users trying to trick an AI into bypassing its built-in safety restrictions and generating harmful content. Glean's advanced detection models can identify these attempts with an impressive 97.8% accuracy. This multi-layered security approach helps enterprises stay protected from constantly evolving AI threats.