Abstract
Recent works have shown the effectiveness of Large Vision Language Models (VLMs or LVLMs) in image manipulation detection. However, text manipulation detection is largely missing in these studies. We bridge this knowledge gap by analyzing closed- and open-source VLMs on different text manipulation datasets. Our results suggest that open-source models are getting closer, but still behind closed-source ones like GPT- 4o. Additionally, we benchmark image manipulation detection-specific VLMs for text manipulation detection and show that they suffer from the generalization problem. We benchmark VLMs for manipulations done on in-the-wild scene texts and on fantasy ID cards, where the latter mimic a challenging real-world misuse.
Abstract (translated)
最近的研究表明，大型视觉语言模型（VLM或LVLM）在图像篡改检测方面非常有效。然而，在这些研究中，对于文本篡改的检测则较少涉及。我们通过分析闭源和开源的VLM模型在不同文本篡改数据集上的表现来填补这一知识空白。我们的结果显示，尽管开源模型正在迎头赶上，但它们仍落后于如GPT-4o这样的闭源模型。此外，我们还针对专门用于图像篡改检测的VLM进行了基准测试，并展示了这些模型在文本篡改检测方面存在泛化问题。我们在野外场景文本和幻想身份证件上的操作中对VLM进行了基准测试，后者模拟了一个具有挑战性的现实世界滥用案例。
URL
https://arxiv.org/abs/2509.10278
