基於多模态大語言模型中的紮根推理實現可解釋且可靠的AI生成圖像檢測

摘要

圖像生成技術的快速發展加劇了對可解釋且穩健的檢測方法的需求。儘管現有方法通常能達到高準確率，但它們往往作為黑箱運作，無法提供人類可理解的解釋。多模態大型語言模型（MLLMs）雖然最初並非為偽造檢測設計，但展現出強大的分析和推理能力。經過適當微調後，它們能有效識別AI生成的圖像並提供有意義的解釋。然而，現有的MLLMs仍存在幻覺問題，且其視覺解釋往往無法與實際圖像內容及人類推理保持一致。為彌合這一差距，我們構建了一個包含AI生成圖像的數據集，並標註了邊界框和描述性標題，以突出合成偽影，為人類對齊的視覺-文本基礎推理奠定基礎。隨後，我們通過多階段優化策略對MLLMs進行微調，逐步平衡準確檢測、視覺定位和連貫文本解釋的目標。最終模型在檢測AI生成圖像和定位視覺缺陷方面均表現優異，顯著超越了基線方法。

English

The rapid advancement of image generation technologies intensifies the demand for interpretable and robust detection methods. Although existing approaches often attain high accuracy, they typically operate as black boxes without providing human-understandable justifications. Multi-modal Large Language Models (MLLMs), while not originally intended for forgery detection, exhibit strong analytical and reasoning capabilities. When properly fine-tuned, they can effectively identify AI-generated images and offer meaningful explanations. However, existing MLLMs still struggle with hallucination and often fail to align their visual interpretations with actual image content and human reasoning. To bridge this gap, we construct a dataset of AI-generated images annotated with bounding boxes and descriptive captions that highlight synthesis artifacts, establishing a foundation for human-aligned visual-textual grounded reasoning. We then finetune MLLMs through a multi-stage optimization strategy that progressively balances the objectives of accurate detection, visual localization, and coherent textual explanation. The resulting model achieves superior performance in both detecting AI-generated images and localizing visual flaws, significantly outperforming baseline methods.

基於多模态大語言模型中的紮根推理實現可解釋且可靠的AI生成圖像檢測

Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs

摘要

Support