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

TL;DR

This paper introduces Foundation-Sec-8B-Instruct, a cybersecurity-focused language model designed for dialogue and instruction-following, outperforming previous models on cybersecurity tasks and matching GPT-4o-mini in relevant areas.

Contribution

The paper presents a new cybersecurity-oriented LLM, Foundation-Sec-8B-Instruct, optimized for conversational use and instruction-following, building upon and improving previous models.

Findings

Outperforms Llama 3.1-8B-Instruct on cybersecurity tasks

Matches instruction-following performance of Llama 3.1-8B-Instruct

Competitive with GPT-4o-mini on cyber threat intelligence

Abstract

Large language models (LLMs) have shown remarkable success across many domains, yet their integration into cybersecurity applications remains limited due to a lack of general-purpose cybersecurity data, representational complexity, and safety and regulatory concerns. To address this gap, we previously introduced Foundation-Sec-8B, a cybersecurity-focused LLM suitable for fine-tuning on downstream tasks. That model, however, was not designed for chat-style interactions or instruction-following. In this report, we release Foundation-Sec-8B-Instruct: a model specifically trained for general-purpose cybersecurity dialogue. Built on Foundation-Sec-8B, it combines domain-specific knowledge with instruction-following, conversational capabilities, and alignment with human preferences to produce high-quality, relevant responses. Comprehensive evaluations show that Foundation-Sec-8B-Instruct outperforms Llama 3.1-8B-Instruct on a range of cybersecurity tasks while matching its instruction-following performance. It is also competitive with GPT-4o-mini on cyber threat intelligence and instruction-following tasks. We envision Foundation-Sec-8B-Instruct becoming an indispensable assistant in the daily workflows of cybersecurity professionals. We release the model publicly at https://huggingface.co/fdtn-ai/Foundation-Sec-8B-Instruct.