Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ruiz-Ródenas, Álvaro, Sáez, Jaime Pujante, García-Algora, Daniel, Béjar, Mario Rodríguez, Blasco, Jorge, Hernández-Ramos, José Luis
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2507.16852
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913955176251392
author Ruiz-Ródenas, Álvaro
Sáez, Jaime Pujante
García-Algora, Daniel
Béjar, Mario Rodríguez
Blasco, Jorge
Hernández-Ramos, José Luis
author_facet Ruiz-Ródenas, Álvaro
Sáez, Jaime Pujante
García-Algora, Daniel
Béjar, Mario Rodríguez
Blasco, Jorge
Hernández-Ramos, José Luis
contents Cyber Threat Intelligence (CTI) mining involves extracting structured insights from unstructured threat data, enabling organizations to understand and respond to evolving adversarial behavior. A key task in CTI mining is mapping threat descriptions to MITRE ATT\&CK techniques. However, this process is often performed manually, requiring expert knowledge and substantial effort. Automated approaches face two major challenges: the scarcity of high-quality labeled CTI data and class imbalance, where many techniques have very few examples. While domain-specific Large Language Models (LLMs) such as SecureBERT have shown improved performance, most recent work focuses on model architecture rather than addressing the data limitations. In this work, we present SynthCTI, a data augmentation framework designed to generate high-quality synthetic CTI sentences for underrepresented MITRE ATT\&CK techniques. Our method uses a clustering-based strategy to extract semantic context from training data and guide an LLM in producing synthetic CTI sentences that are lexically diverse and semantically faithful. We evaluate SynthCTI on two publicly available CTI datasets, CTI-to-MITRE and TRAM, using LLMs with different capacity. Incorporating synthetic data leads to consistent macro-F1 improvements: for example, ALBERT improves from 0.35 to 0.52 (a relative gain of 48.6\%), and SecureBERT reaches 0.6558 (up from 0.4412). Notably, smaller models augmented with SynthCTI outperform larger models trained without augmentation, demonstrating the value of data generation methods for building efficient and effective CTI classification systems.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16852
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SynthCTI: LLM-Driven Synthetic CTI Generation to enhance MITRE Technique Mapping
Ruiz-Ródenas, Álvaro
Sáez, Jaime Pujante
García-Algora, Daniel
Béjar, Mario Rodríguez
Blasco, Jorge
Hernández-Ramos, José Luis
Cryptography and Security
Artificial Intelligence
Machine Learning
Cyber Threat Intelligence (CTI) mining involves extracting structured insights from unstructured threat data, enabling organizations to understand and respond to evolving adversarial behavior. A key task in CTI mining is mapping threat descriptions to MITRE ATT\&CK techniques. However, this process is often performed manually, requiring expert knowledge and substantial effort. Automated approaches face two major challenges: the scarcity of high-quality labeled CTI data and class imbalance, where many techniques have very few examples. While domain-specific Large Language Models (LLMs) such as SecureBERT have shown improved performance, most recent work focuses on model architecture rather than addressing the data limitations. In this work, we present SynthCTI, a data augmentation framework designed to generate high-quality synthetic CTI sentences for underrepresented MITRE ATT\&CK techniques. Our method uses a clustering-based strategy to extract semantic context from training data and guide an LLM in producing synthetic CTI sentences that are lexically diverse and semantically faithful. We evaluate SynthCTI on two publicly available CTI datasets, CTI-to-MITRE and TRAM, using LLMs with different capacity. Incorporating synthetic data leads to consistent macro-F1 improvements: for example, ALBERT improves from 0.35 to 0.52 (a relative gain of 48.6\%), and SecureBERT reaches 0.6558 (up from 0.4412). Notably, smaller models augmented with SynthCTI outperform larger models trained without augmentation, demonstrating the value of data generation methods for building efficient and effective CTI classification systems.
title SynthCTI: LLM-Driven Synthetic CTI Generation to enhance MITRE Technique Mapping
topic Cryptography and Security
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2507.16852