Arc Sentry 在直接對標測試中以 92% 對 70% 的檢測率超越 LLM Guard，以下是其運作原理。

I built Arc Sentry, a pre-generation prompt injection detector for open-weight LLMs. Instead of scanning text for patterns after the fact, it reads the model’s internal residual stream before generate() is called and blocks requests that destabilize the model’s information geometry. Head to head benchmark on a 130-prompt SaaS deployment dataset: Arc Sentry: 92% detection, 0% false positives LLM Guard: 70% detection, 3.3% false positives The difference is architectural. LLM Guard classifies i