The reviewed record of science sign in
Pith

arxiv: 2508.01059 · v1 · pith:WP6QU6TE · submitted 2025-08-01 · cs.CR · cs.AI

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

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:WP6QU6TErecord.jsonopen to challenge →

classification cs.CR cs.AI
keywords cybersecurityfoundation-sec-8b-instructinstruction-followingmodeltasksfoundation-sec-8bgeneral-purposerelease
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines

    cs.SE 2026-06 unverdicted novelty 7.0

    FAPO automates LLM pipeline optimization via iterative diagnosis and prompt-or-structure edits, beating GEPA baseline by +14.1 pp mean across 18 comparisons and +33.8 pp when structural changes occur.

  2. Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills

    cs.CR 2026-05 unverdicted novelty 7.0

    Malicious Skills induce coding agents to hallucinate and import attacker-controlled packages at high rates while evading detection.

  3. Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation

    cs.CR 2026-06 unverdicted novelty 5.0

    Fine-tuning security LLMs specializes inherited classification circuits into token-level indicators that preserve canonical accuracy but fail under behavior-preserving transformations like aliasing and case mutation.

  4. LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning

    cs.LG 2026-06 unverdicted novelty 5.0

    The paper reformulates industrial continual learning for LLMs as a closed-loop ecosystem problem, identifies three core challenges, and organizes solutions around five lifecycle design principles.

  5. Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights

    cs.CR 2026-05 unverdicted novelty 3.0

    Domain-adapted LLMs and SLMs do not consistently outperform general models on STRIDE threat classification for 5G, with decoding strategies and model scale affecting validity but gains remaining insufficient for reliable use.