Agentic AI Reference Architecture

Model Adaptation · Software component

Adversarial Simulation Agent

Software componentModel AdaptationModelsarc:AdversarialSimulationAgent

A simulated participant agent (legitimate or fraudulent) that generates transactions, with fraud variants evolving evasion tactics.

Responsibility. Generates realistic legitimate and evasive fraudulent activity for training and testing.

Also known as: Transaction Agent, Fraud Agent

producesSynthetic Dataset: producesSynthetic Dataset
Direct neighbourhood (hover for relationship types)

Relationships

produces lifecycle

Classification

Patterns
Adversarial coevolutionMultiverse simulation
Quality attributes
Functional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)Performance efficiency (ISO/IEC 25010)
Risks mitigated
Scarce labelled fraud data

Sources

  1. Ref1.05: Q. Wang, W. T. Tsai, T. Shi, Z. Liu, and B. Du, "Catch me if you can: A multi-agent synthetic fraud detection framework for complex networks," in Proc. IEEE 41st Int. Conf. Data Eng. (ICDE), 2025, pp. 3629-3641, doi: 10.1109/ICDE65448.2025.00271.