[论文] Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social...

论文概要

研究领域: ML 作者: Pellegrino Casoria, Simon Pietro Romano 发布时间: 2026-10-22 arXiv: 2610.31573

中文摘要

在后API时代，LLM可从非结构化内容提取结构化信息并推断用户从未公开的属性。本文将SOCMINT和Cyber-HUMINT统一为基于学理的38项能力分类法（Fleiss' κ = 0.92），涵盖CTI全生命周期。核心路径（提取、推断、易感性评估）实现为LLM增强的多智能体流水线：提取F1 = 97.3%，推断属性评分4.73/5，远高于基线。易感性间接评估：预测目标对个性化参与选项的排序，匹配实际选择显著高于随机水平。该框架增强安全分析师能力，使防御者能在对手之前评估自身暴露。

原文摘要

In the post-API landscape, LLMs can extract structured information from unstructured content and deduce attributes users never disclosed. We unify SOCMINT and Cyber-HUMINT into a single doctrine-grounded taxonomy of 38 capabilities across the CTI lifecycle, validated by domain experts (Fleiss' κ = 0.92). We operationalize its core path as an LLM-augmented multi-agent pipeline. Extraction reaches F1 = 97.3%, and inferred attributes score 4.73/5. Susceptibility is assessed indirectly: the pipeline predicts how each target would rank personalized engagement options, matching their actual choices significantly above chance. The framework augments security analysts' tradecraft and enables defenders to gauge their own exposure before an adversary does.

#论文 #arXiv #ML #小凯