Newest papers

Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure

Pellegrino Casoria, Simon Pietro Romano · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31573 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Dalam landscape post-API yang sangat mendasar, profiling media sosial telah menjadi murah dan otomatis: Model Target Berbasis Bahasa Besar (LLM) dapat mengekstrak informasi terstruktur dari konten inti yang tidak terstruktur dan menyimpulkan atribut pengguna yang tidak pernah diungkapkan. Eksposur nyata seseorang bukanlah apa yang mereka posting, tetapi apa yang dapat disimpulkan dari itu. Karena praktek-praktek ini menjadi rutin, eksposur terhadap serangan teknik sosial menjadi kepastian operasional, menuntut kerangka kerja yang dibagikan untuk evaluasi dan mitigasi. Kami membuat eksposur ini dapat diukur dengan mengukur seberapa akurat target dapat diprofil, dan seberapa jauh profil itu memungkinkan serangan teknik sosial. Karena tidak ada model yang benar-benar ada yang mencakup kontinuum ini, kami menyatukan Social Media Intelligence (SOCMINT) dan Cyber Intelligence

Machine translation (Meta M2M100); the English original follows.

Abstract

In the post-API landscape, social-media profiling has become inexpensive and automated: Large Language Models (LLMs) can extract structured information from unstructured content and deduce attributes users never disclosed. A person's true exposure is not what they post but what can be inferred from it. As these practices become routine, exposure to social engineering attacks becomes an operational certainty, demanding a shared framework for assessment and mitigation. We make this exposure measurable by quantifying how accurately a target can be profiled, and how far that profile enables social engineering attacks. Because no existing model fully spans this continuum, we unify Social Media Intelligence (SOCMINT) and Cyber Human Intelligence (Cyber-HUMINT), two individual-focused disciplines that evolved separately, into a single doctrine-grounded taxonomy of 38 capabilities across the Cyber Threat Intelligence lifecycle, where user profiling bridges passive collection and active engagement. Domain experts validated the taxonomy (Fleiss' $κ$ = 0.92). We operationalize its core path (extraction, inference, and susceptibility assessment) as an LLM-augmented multi-agent pipeline, evaluated on real participants' public data. Susceptibility is assessed indirectly: the pipeline predicts how each target would rank personalized engagement options, matching their actual choices significantly above chance. This ranking capacity captures the personalization on which tailored attacks depend. The underlying profiles are accurate: extraction reaches F1 = 97.3%, and inferred attributes score 4.73/5, both far above rule-based and NER-based baselines at negligible cost. The framework augments security analysts' tradecraft rather than replacing it and enables defenders to gauge their own exposure before an adversary does.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Profiling (computer programming), Personalization, Social media, Operationalization, Adversary

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange