Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report
read the original abstract
As transformer-based large language models (LLMs) increasingly permeate society, they have revolutionized domains such as software engineering, creative writing, and digital arts. However, their adoption in cybersecurity remains limited due to challenges like scarcity of specialized training data and complexity of representing cybersecurity-specific knowledge. To address these gaps, we present Foundation-Sec-8B, a cybersecurity-focused LLM built on the Llama 3.1 architecture and enhanced through continued pretraining on a carefully curated cybersecurity corpus. We evaluate Foundation-Sec-8B across both established and new cybersecurity benchmarks, showing that it matches Llama 3.1-70B and GPT-4o-mini in certain cybersecurity-specific tasks. By releasing our model to the public, we aim to accelerate progress and adoption of AI-driven tools in both public and private cybersecurity contexts.
This paper has not been read by Pith yet.
Forward citations
Cited by 11 Pith papers
-
Cybersecurity AI (CAI) Dataset
CAI Dataset is presented as the largest described corpus of LLM-driven hacker trajectories, with the claim that operator data concentration in frontier-model providers creates a major security risk best addressed by o...
-
ShellGames: Speculative LLM-Driven SSH Deception
ShellGames is an LLM-based SSH shell simulator that integrates five techniques to achieve 0.898 command accuracy, 0.918 sequence consistency, 0.98 state tracking, and 0.95 robustness on a new benchmark, plus comparabl...
-
Closing the Sim-to-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDR
Introduces an evaluation framework for autonomous defense agents hardening commercial EDR, tested in a GOAD lab with Microsoft Defender XDR and two LLMs, revealing three lessons on telemetry design, per-policy attribu...
-
A Red Teaming Framework for Evaluating Robustness of AI-enabled Security Orchestration, Automation, and Response Systems
A hybrid LLM-RL red teaming framework generates adaptive attack campaigns in simulated enterprise networks to evaluate the robustness of AI-enabled SOAR systems.
-
Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
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.
-
LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy
ACSE estimates LLM uncertainty via adaptive semantic entropy clustering with conformal prediction guarantees, reporting higher AUROC than token entropy baselines on datasets like TriviaQA.
-
LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy
ACSE estimates LLM prompt uncertainty via adaptive clustering of semantic entropy across multiple responses and uses conformal prediction to bound error rates on accepted answers with distribution-free guarantees.
-
Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026
KIT's IWSLT submission uses segment concatenation, LLM label generation and cross-lingual translation to create >1M long-form training instances and shows that likelihood re-ranking harms semantic tasks unless combine...
-
Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices
CORE is a lightweight two-stage prompt compression method for edge-device RAG QA that builds answer and clue sets via NER and semantic matching then refines them to deliver higher accuracy and lower resource costs tha...
-
Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights
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.
-
XekRung Technical Report
XekRung achieves state-of-the-art performance on cybersecurity benchmarks among same-scale models via tailored data synthesis and multi-stage training while retaining strong general capabilities.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.