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

• URL: http://arxiv.org/abs/2506.07045v1
• Date: Sun, 08 Jun 2025 08:47:44 GMT
• Title: Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs
• Authors: Yikun Ji, Hong Yan, Jun Lan, Huijia Zhu, Weiqiang Wang, Qi Fan, Liqing Zhang, Jianfu Zhang,
• Abstract summary: We build a dataset of AI-generated images annotated with bounding boxes and descriptive captions.<n>We then finetune MLLMs through a multi-stage optimization strategy.<n>The resulting model achieves superior performance in both detecting AI-generated images and localizing visual flaws.
• Score: 43.08776932101172
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Models [82.04858317800097]
  We present ForenX, a novel method that not only identifies the authenticity of images but also provides explanations that resonate with human thoughts.<n>ForenX employs the powerful multimodal large language models (MLLMs) to analyze and interpret forensic cues.<n>We introduce ForgReason, a dataset dedicated to descriptions of forgery evidences in AI-generated images.
  arXiv  Detail & Related papers  (2025-08-02T15:21:26Z)
• Text-Visual Semantic Constrained AI-Generated Image Quality Assessment [47.575342788480505]
  We propose a unified framework to enhance the comprehensive evaluation of both text-image consistency and perceptual distortion in AI-generated images.<n>Our approach integrates key capabilities from multiple models and tackles the aforementioned challenges by introducing two core modules.<n>Tests conducted on multiple benchmark datasets demonstrate that SC-AGIQA outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-07-14T16:21:05Z)
• AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models [78.08374249341514]
  The rapid development of AI-generated content (AIGC) has led to the misuse of AI-generated images (AIGI) in spreading misinformation.<n>We introduce a large-scale and comprehensive dataset, Holmes-Set, which includes an instruction-tuning dataset with explanations on whether images are AI-generated.<n>Our work introduces an efficient data annotation method called the Multi-Expert Jury, enhancing data generation through structured MLLM explanations and quality control.<n>In addition, we propose Holmes Pipeline, a meticulously designed three-stage training framework comprising visual expert pre-training, supervised fine-tuning, and direct preference optimization
  arXiv  Detail & Related papers  (2025-07-03T14:26:31Z)
• Perceptual Decoupling for Scalable Multi-modal Reasoning via Reward-Optimized Captioning [78.17782197231325]
  We propose a reasoning-guided reinforcement learning strategy that aligns the extractor's captioning behavior with the reasoning objective.<n> Experiments on multi-modal math and science benchmarks show that the proposed RACRO method achieves state-of-the-art average performance.
  arXiv  Detail & Related papers  (2025-06-05T02:28:07Z)
• The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts [17.31556625041178]
  multimedia manipulation has emerged as a critical challenge in combating AI-generated disinformation.<n>We propose a new adversarial pipeline that MLLMs to generate high-risk disinformation.<n>We present the Artifact-aware Manipulation Diagnosis Diagnosis via MLLM framework.
  arXiv  Detail & Related papers  (2025-05-23T04:58:27Z)
• FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensics [66.14786900470158]
  We propose FakeScope, an expert multimodal model (LMM) tailored for AI-generated image forensics.<n>FakeScope identifies AI-synthetic images with high accuracy and provides rich, interpretable, and query-driven forensic insights.<n>FakeScope achieves state-of-the-art performance in both closed-ended and open-ended forensic scenarios.
  arXiv  Detail & Related papers  (2025-03-31T16:12:48Z)
• TruthLens:A Training-Free Paradigm for DeepFake Detection [4.64982780843177]
  We introduce TruthLens, a training-free framework that reimagines deepfake detection as a visual question-answering (VQA) task.<n>TruthLens utilizes state-of-the-art large vision-language models (LVLMs) to observe and describe visual artifacts.<n>By adopting a multimodal approach, TruthLens seamlessly integrates visual and semantic reasoning to not only classify images as real or fake but also provide interpretable explanations.
  arXiv  Detail & Related papers  (2025-03-19T15:41:32Z)
• VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models [14.053424085561296]
  Face models with high-quality and controllable attributes pose a significant challenge for Deepfake detection.<n>In this work, we integrate Multimodal Large Language Models (MLLMs) within DM-based face forensics.<n>We propose a fine-grained analysis triad framework called VLForgery, that can 1) predict falsified facial images; 2) locate the falsified face regions subjected to partial synthesis; and 3) attribute the synthesis with specific generators.
  arXiv  Detail & Related papers  (2025-03-08T09:55:19Z)
• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning [63.0285363282581]
  Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information.<n>We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning.<n>We reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning.
  arXiv  Detail & Related papers  (2025-02-25T23:36:19Z)
• Bi-LORA: A Vision-Language Approach for Synthetic Image Detection [14.448350657613364]
  Deep image synthesis techniques, such as generative adversarial networks (GANs) and diffusion models (DMs) have ushered in an era of generating highly realistic images. This paper takes inspiration from the potent convergence capabilities between vision and language, coupled with the zero-shot nature of vision-language models (VLMs) We introduce an innovative method called Bi-LORA that leverages VLMs, combined with low-rank adaptation (LORA) tuning techniques, to enhance the precision of synthetic image detection for unseen model-generated images.
  arXiv  Detail & Related papers  (2024-04-02T13:54:22Z)
• mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections [104.14624185375897]
  mPLUG is a new vision-language foundation model for both cross-modal understanding and generation. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, such as image captioning, image-text retrieval, visual grounding and visual question answering.
  arXiv  Detail & Related papers  (2022-05-24T11:52:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.