Hugging Face BlogT1·Models
68 pts
ServiceNow AI has released and open-sourced AprielGuard, an 8B parameter safety-security safeguard model designed for modern LLM systems. It detects 16 categories of safety risks (e.g., toxicity, hate speech) and a wide range of adversarial attacks, including prompt injections and jailbreaks, providing a unified risk assessment framework for agentic systems.