# A Benchmark Dataset for MLLM-Generated Image Detection: GPT Image2 & Nano Banana2

arXiv: https://arxiv.org/abs/2608.01258 · HTML: https://mlsanity.com/paper/2608.01258/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 19 of 19)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Towards Universal Fake Image Detectors that Generalize Across Generative Models](https://mlsanity.com/paper/2302.10174/) (2023)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image](https://mlsanity.com/paper/2306.08571/) (2023)
- [Raising the Bar of AI-generated Image Detection with CLIP](https://mlsanity.com/paper/2312.00195/) (2023)
- [A Survey on Generative Adversarial Networks: Variants, Applications, and Training](https://mlsanity.com/paper/2006.05132/) (2020)
- [Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios](https://mlsanity.com/paper/2509.09172/) (2025)
- [CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey](https://mlsanity.com/paper/2504.14280/) (2025)
- [AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detection](https://mlsanity.com/paper/2504.20865/) (2025)
- [Towards Generalizable AI-Generated Image Detection via Image-Adaptive Prompt Learning](https://mlsanity.com/paper/2508.01603/) (2025)
- [Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes](https://mlsanity.com/paper/2512.12982/) (2025)
- [PGC: Peak-Guided Calibration for Generalizable AI-Generated Image Detection](https://mlsanity.com/paper/2605.21207/) (2026)
- [Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection](https://mlsanity.com/paper/2603.10598/) (2026)
- [TextFake: Benchmarking AI-Generated Image Detection on Text-Rich Images](https://mlsanity.com/paper/2606.01050/) (2026)

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

- [ChatGPT Images 2.5 in the Wild: A Launch-Period Dataset and Detector Evaluation](https://mlsanity.com/paper/2609.15100/) (2026)
- [Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection](https://mlsanity.com/paper/2610.08639/) (2026)

## Abstract (arXiv)

The realism of images generated by multimodal large language models (MLLMs), such as GPT Image2 and Nano Banana2, has improved rapidly in recent years. Compared with early generative models, current models have made clear progress in text rendering. They can produce high-quality images that closely resemble real-world application scenarios. The enhanced generation capabilities of current MLLMs pose increasingly severe challenges to AI-generated image detection. Detection is no longer limited to identifying obvious artifacts left by early generators. Instead, it requires systematic and realistic benchmarks for the new generation of generated content. However, most existing benchmarks are still built around early generative models and cannot fully evaluate the forensic challenges introduced by high-quality and multi-form generated images. To address this gap, this paper constructs a benchmark dataset for detecting images generated by MLLMs. The benchmark covers several realistic application scenarios and adopts three generation protocols to simulate direct generation, reference-based reconstruction, and local editing. Based on this benchmark, we evaluate detector degradation from traditional scenarios to MLLM-generated images and analyze false positive rates and false negative rates across three sample types, revealing the failure modes of existing methods. We further propose a structural-artifact-prior-guided dual-stream prompt framework (SAP-DSP) as a strong baseline. SAP-DSP uses dual-stream prompt learning and structure-aware routing fusion to improve representation learning. Extensive experiments show that the proposed benchmark exposes the performance degradation of existing detectors on high-quality generated images, while SAP-DSP achieves more stable detection results on this benchmark. Our code and dataset are publicly available at https://github.com/xbrainnet/SAP-DSP.