Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report

TL;DR

This paper introduces Foundation-Sec-8B-Reasoning, an open-source cybersecurity reasoning model built on Llama-3.1, trained with a two-stage process, achieving competitive performance on cybersecurity and general reasoning tasks.

Contribution

It presents the first open-source native reasoning model for cybersecurity, combining proprietary data and a two-stage training process to balance domain-specific and general capabilities.

Findings

Competitive performance on cybersecurity benchmarks

Strong generalization on multi-hop reasoning tasks

Effective safety performance with system prompts

Abstract

We present Foundation-Sec-8B-Reasoning, the first open-source native reasoning model for cybersecurity. Built upon our previously released Foundation-Sec-8B base model (derived from Llama-3.1-8B-Base), the model is trained through a two-stage process combining supervised fine-tuning (SFT) and reinforcement learning from verifiable rewards (RLVR). Our training leverages proprietary reasoning data spanning cybersecurity analysis, instruction-following, and mathematical reasoning. Evaluation across 10 cybersecurity benchmarks and 10 general-purpose benchmarks demonstrates performance competitive with significantly larger models on cybersecurity tasks while maintaining strong general capabilities. The model shows effective generalization on multi-hop reasoning tasks and strong safety performance when deployed with appropriate system prompts and guardrails. This work demonstrates that domain-specialized reasoning models can achieve strong performance on specialized tasks while maintaining broad general capabilities. We release the model publicly at https://huggingface.co/fdtn-ai/Foundation-Sec-8B-Reasoning.