FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence

TL;DR

FraudBench is a new multimodal benchmark designed to evaluate AI and human ability to detect AI-generated fraudulent refund evidence across various real-world scenarios.

Contribution

The paper introduces FraudBench, a comprehensive benchmark dataset for claim-conditioned detection of AI-generated fraudulent evidence, combining real and synthetic images with metadata.

Findings

Current models recognize real damage but struggle with fake damage detection.

Fake-damage detection rates are often below 50% on most generators.

Specialized detectors outperform generic models but still show inconsistency.

Abstract

Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to concrete real-world claims, creating new challenges for verifying visual evidence. A concrete emerging risk is AI-generated refund fraud, in which manipulated or synthetic images are used to support claims about damaged products, poor delivery conditions, or service-related defects. Existing AI-generated image detection benchmarks mainly evaluate standalone authenticity classification, cross-generator transfer, or forensic localization, leaving claim-conditioned fraudulent evidence detection underexplored. To bridge this gap, we introduce FraudBench, a multimodal benchmark for detecting AI-generated fraudulent refund evidence. FraudBench is constructed from real-world user-review evidence across e-commerce, food delivery, and travel-service scenarios. We curate real evidence images together with their associated review and product metadata, identify genuine damaged and undamaged evidence through MLLM-assisted filtering and human annotation, and synthesize fake-damaged evidence from genuine undamaged reference images using six state-of-the-art image editing and generation models. Using FraudBench, we evaluate MLLMs, specialized AI-generated image detectors, and human participants under the same settings. Experiments show that current MLLMs often recognize real-damaged evidence but fail on many fake-damaged subsets, with fake-damage detection rates (TPR) far below the 50% baseline on most generator subsets. Specialized detectors generally perform better but remain inconsistent across generators and can produce false positives on real-damaged samples, revealing a clear gap between generic AI image detection and reliable claim-conditioned refund-evidence verification.