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

arXiv: https://arxiv.org/abs/2605.08820 · HTML: https://mlsanity.com/paper/2605.08820/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 49 references that are in the map.
- First posted on arXiv 9 May 2026.

## Builds on (most cited first, 3 of 3)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)

## Built on by (most cited first, 2 of 2)

- [Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection](https://mlsanity.com/paper/2607.27113/) (2026)
- [Evi-VN: Hard Region Guided Virtual Node Evidence Injection for GNN-Based Fraud Detection](https://mlsanity.com/paper/2610.11665/) (2026)

## Abstract (arXiv)

Artificial Intelligence (AI)-generated images have become increasingly realistic and readily adaptable to 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 12 state-of-the-art image editing and generation models. Using FraudBench, we evaluate MLLMs, specialized AI-generated image detectors, and human evaluators on the same evaluation images. 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.