Forensic Schema for Psychological Manipulation in Cyber Fraud: LLM-Driven Victim Reports Analysis

2026-07-08

AI Summary

This study addresses a critical gap in existing cybercrime classification frameworks by systematically incorporating psychological manipulation tactics prevalent in online fraud. The authors propose a novel forensic framework that integrates a structured taxonomy comprising four categories and 35 specific items, combining 11 psychological manipulation indicators with cryptocurrency-related evidence fields. They design a reusable, hierarchical large language model (LLM) annotation template and apply it to over 10,000 victim reports. Using LLM-driven annotation, inter-rater reliability assessment (Cohen’s κ = 0.69), Cramér’s V association analysis (maximum value = 0.790), and rationale-based evidentiary auditing, the study reveals distinct psychological manipulation profiles across fraud types and identifies a pervasive absence of crucial forensic details in victim narratives.

Abstract

Existing cybercrime classification schemas capture contact metadata and financial transactions but omit the psychological manipulation techniques perpetrators employ. We present a forensic schema (four categories, 35 questions) adding 11 manipulation indicators and cryptocurrency evidence fields to established forensic foundations. Applied to 10,994 victim reports via large language model (LLM)-driven annotation and validated against two human annotators (mean LLM-human $κ= 0.69$, matching inter-annotator $κ= 0.68$), the schema revealed a statistically distinct manipulation profile for each major fraud type (Cramer's $V$ up to $0.790$). A rationale-based evidence audit nonetheless exposed a forensic detail gap: detection of manipulation techniques was reliable, but victim narratives varied widely in the actionable detail supporting each Yes answer, and blockchain-specific identifiers were nearly absent. These findings point to AI-assisted victim intake with schema-informed follow-up questions as the most direct way to close the gap. The tiered annotation strategy also provides a reusable template for LLM-based extraction from other forensic text domains.

Problem

• psychological manipulation
• cyber fraud
• forensic schema
• victim reports
• LLM-driven analysis

Innovation

• forensic schema
• psychological manipulation
• large language model (LLM)
• cyber fraud
• victim report analysis