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

AprielGuard is available in both reasoning and non-reasoning modes, enabling explainable classification when needed and low-latency classification for production pipelines.

Traditional safety classifiers primarily focus on a limited classification spectrum (e.g., toxicity or self-harm), assume short inputs, and evaluate single user messages. Modern deployments, however, feature:

As a result, production teams increasingly rely on workarounds: multiple guard models for different stages, regex filters, static rules, or hand-crafted heuristics. These approaches are brittle and do not scale.

AprielGuard addresses these issues with a unified model and a unified safety + adversarial taxonomy, built specifically for modern LLM agent ecosystems.

The model detects and evaluates a wide range of adversarial prompt patterns designed to manipulate model behavior or evade safety mechanisms. The model outputs a binary classification (e.g., adversarial / non_adversarial) rather than fine-grained attack categories.

The training data covers diverse adversarial types such as role-playing, world-building, persuasion, and stylization, among many other complex prompt manipulation strategies. These examples represent only a subset of the broader adversarial scenarios incorporated in the training data.

Synthetic data : AprielGuard is trained on a synthetically generated training dataset. The training data points are generated at a sub-topic level of the taxonomy for better coverage. We leverage Mixtral-8x7B and internally developed uncensored models to generate unsafe content for training purposes. Models were prompted with higher temperature to induce output variation. Prompting templates are meticulously tailored to ensure accurate data generation.

Source link