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

Summary

Researchers present Social-HUMINT, an LLM-augmented framework that measures how accurately a person can be profiled from public social media data and how far that profile enables social engineering. They unify SOCMINT and Cyber-HUMINT into a 38-capability taxonomy validated by domain experts (Fleiss' κ = 0.92). A multi-agent pipeline reached F1 = 97.3% for extraction and 4.73/5 for inferred attributes, and predicted participants' engagement choices above chance.

Related items

• InfoAfterDeleteBench: Auditing Post-Deletion Information Persistence in LLM AgentsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• HighCVE-2026-111079: Goose sends unsanitized terminal history to LLM provider endpointsSimilar attack · NVD/CVE Database
• LowAgent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM SystemsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• Medium“Next Exploit Opportunities”: How a Threat Actor Used AI to Help Plan and Execute Multiple Types of Cybercrime ActivitiesSimilar attack · Palo Alto Unit 42
• MediumA Design Flaw in Share Links Exposes Users’ Personal Conversations With Meta’s MuseSimilar attack · Wired (Security)