# Hugging Face — AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems

- Company: Hugging Face (huggingface.co)
- Announced: 2025-12-23T14:07:35+00:00
- Category: new-model
- Subject: Platform
- Models affected: AprielGuard
- Source: https://huggingface.co/blog/ServiceNow-AI/aprielguard
- Record: https://forck.live/items/1568-aprielguard-a-guardrail-for-safety-and-adversarial-robustness-in-modern-llm

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.

## Evidence

Verbatim from https://huggingface.co/blog/ServiceNow-AI/aprielguard:

> In this work, we introduce AprielGuard, an 8B parameter safety–security safeguard model designed to detect:

---

Record: https://forck.live/items/1568-aprielguard-a-guardrail-for-safety-and-adversarial-robustness-in-modern-llm
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md