From the source
ServiceNow AI introduced AprielGuard, an 8B parameter safety–security safeguard model designed to detect 16 categories of safety risks and a wide range of adversarial attacks, available in reasoning and non-reasoning modes.
AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems
New model
From the source
In this work, we introduce AprielGuard, an 8B parameter safety–security safeguard model designed to detect:
huggingface.co
