FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910204900147200 |
|---|---|
| author | Yan, Xinyu Chen, Boyang Zhang, Jiaming Wu, Tiantong Tae, Hong Xi He, Yichen Wang, Tiantong Mi, Yachun Hao, Yurong Zhao, Yilei Xiao, Lei Huang, Longtao Xie, Pengjun Liu, Wei Lim, Wei Yang Bryan |
| author_facet | Yan, Xinyu Chen, Boyang Zhang, Jiaming Wu, Tiantong Tae, Hong Xi He, Yichen Wang, Tiantong Mi, Yachun Hao, Yurong Zhao, Yilei Xiao, Lei Huang, Longtao Xie, Pengjun Liu, Wei Lim, Wei Yang Bryan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08820 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence Yan, Xinyu Chen, Boyang Zhang, Jiaming Wu, Tiantong Tae, Hong Xi He, Yichen Wang, Tiantong Mi, Yachun Hao, Yurong Zhao, Yilei Xiao, Lei Huang, Longtao Xie, Pengjun Liu, Wei Lim, Wei Yang Bryan Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security 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. |
| title | FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2605.08820 |