Lead story
Models & availability
Latest
← Feed
Copy✕ Close copy menu
AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems
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.
From the source
In this work, we introduce AprielGuard, an 8B parameter safety–security safeguard model designed to detect:
huggingface.co
Visit source ↗huggingface.co
- Announced
- 23 Dec 2025 14:07 UTC
- Detected
- 03 Aug 2026 21:12 UTC (+223d after)