PromptForge-350k: A Large-Scale Dataset and Contrastive Framework for Prompt-Based AI Image Forgery Localization

• URL: http://arxiv.org/abs/2603.29386v1
• Date: Tue, 31 Mar 2026 07:54:58 GMT
• Title: PromptForge-350k: A Large-Scale Dataset and Contrastive Framework for Prompt-Based AI Image Forgery Localization
• Abstract summary: We introduce a fully automated mask annotating framework to generate precise ground-truth masks for edited regions.<n>We also propose ICL-Net, an effective forgery localization network featuring a triple-stream backbone and intra-image contrastive learning.<n>Our method achieves an IoU of 62.5% on PromptForge-350k, outperforming SOTA methods by 5.1%.
• Score: 20.545082186848287
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid democratization of prompt-based AI image editing has recently exacerbated the risks associated with malicious content fabrication and misinformation. However, forgery localization methods targeting these emerging editing techniques remain significantly under-explored. To bridge this gap, we first introduce a fully automated mask annotating framework that leverages keypoint alignment and semantic space similarity to generate precise ground-truth masks for edited regions. Based on this framework, we construct PromptForge-350k, a large-scale forgery localization dataset covering four state-of-the-art prompt-based AI image editing models, thereby mitigating the data scarcity in this domain. Furthermore, we propose ICL-Net, an effective forgery localization network featuring a triple-stream backbone and intra-image contrastive learning. This design enables the model to capture highly robust and generalizable forensic features. Extensive experiments demonstrate that our method achieves an IoU of 62.5% on PromptForge-350k, outperforming SOTA methods by 5.1%. Additionally, it exhibits strong robustness against common degradations with an IoU drop of less than 1%, and shows promising generalization capabilities on unseen editing models, achieving an average IoU of 41.5%.

Related papers

• Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation [43.1212452324751]
  Existing datasets in this domain either entirely lack descriptive text, or suffer from severe text-image semantic misalignment.<n>We present a novel methodology to construct and automatically validate a large-scale multimodal dataset for disaster response.
  arXiv  Detail & Related papers  (2026-07-30T14:23:01Z)
• Leveraging Image Generators to Address Training Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping [6.12592712646272]
  This paper addresses the dual challenges of data scarcity and extreme class imbalance in the semantic segmentation of fine-grained forest regeneration species.<n>We leverage the large-scale vision-language Nano Banana Pro model to simultaneously generate high-fidelity images and their corresponding pixel-aligned semantic masks from prompts.<n>Our methodology integrates real-world data with AI-generated images, highlighting that AI-generated data is highly complementary to real-world data.
  arXiv  Detail & Related papers  (2026-05-07T03:28:56Z)
• FeatDistill: A Feature Distillation Enhanced Multi-Expert Ensemble Framework for Robust AI-generated Image Detection [14.180599240051238]
  FeatDistill is an AI-generated image detection framework that integrates feature distillation with a multi-expert ensemble.<n>It was developed for the NTIRE Challenge on Robust AI-Generated Image Detection in the Wild.
  arXiv  Detail & Related papers  (2026-03-23T12:55:31Z)
• Supervised Contrastive Learning for Few-Shot AI-Generated Image Detection and Attribution [3.103291412074661]
  This work proposes a novel two-stage detection framework to address the generalization challenge inherent in synthetic image detection.<n>The proposed framework achieves an average detection accuracy of 91.3%, representing a 5.2 percentage point improvement over existing approaches.
  arXiv  Detail & Related papers  (2025-11-20T16:53:24Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotation [49.83611963142304]
  Images manipulated using image editing tools can mislead viewers and pose significant risks to social security.<n>One of the main barriers in this area is the high cost of data acquisition and the severe lack of high-quality annotated datasets.<n>We utilize a large collection of manually forged images from the web, as well as automatically generated annotations.<n>We construct MIMLv2, a large-scale, diverse, and high-quality dataset containing 246,212 manually forged images with pixel-level mask annotations.
  arXiv  Detail & Related papers  (2025-08-28T16:44:40Z)
• SDiFL: Stable Diffusion-Driven Framework for Image Forgery Localization [46.258797633731746]
  Existing image forgery localization methods rely on labor-intensive and costly annotated data.<n>We are the first to integrate both image generation and powerful perceptual capabilities of SD into an image forensic framework.<n>Our framework achieves up to 12% improvements in performance on widely used benchmarking datasets.
  arXiv  Detail & Related papers  (2025-08-27T18:02:09Z)
• No Pixel Left Behind: A Detail-Preserving Architecture for Robust High-Resolution AI-Generated Image Detection [15.139983859649922]
  High-Resolution Detail-Aggregation Network (HiDA-Net) is a novel framework that ensures no pixel is left behind.<n>HiDA-Net achieves state-of-the-art, increasing accuracy by over 13% on the challenging Chameleon dataset and 10% on our HiRes-50K.
  arXiv  Detail & Related papers  (2025-08-24T13:03:16Z)
• CLUE: Leveraging Low-Rank Adaptation to Capture Latent Uncovered Evidence for Image Forgery Localization [35.73353140683283]
  Increasing accessibility of image editing tools and generative AI has led to a proliferation of visually convincing forgeries.<n>In this paper, we repurpose the mechanism of a state-of-the-art (SOTA) text-to-image synthesis model by exploiting its internal generative process.<n>We propose CLUE, a framework that employs Low- Rank Adaptation (LoRA) to parameter-efficiently reconfigure Stable Diffusion 3 (SD3) as a forensic feature extractor.
  arXiv  Detail & Related papers  (2025-08-10T16:22:30Z)
• So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection [75.79507634008631]
  We introduce So-Fake-Set, a social media-oriented dataset with over 2 million high-quality images, diverse generative sources, and imagery synthesized using 35 state-of-the-art generative models.<n>We present So-Fake-R1, an advanced vision-language framework that employs reinforcement learning for highly accurate forgery detection, precise localization, and explainable inference through interpretable visual rationales.
  arXiv  Detail & Related papers  (2025-05-24T11:53:35Z)
• SA-MixNet: Structure-aware Mixup and Invariance Learning for Scribble-supervised Road Extraction in Remote Sensing Images [85.52629779976137]
  We propose a structure-aware Mixup scheme to paste road regions from one image onto another for creating an image scene with increased complexity. A discriminator-based regularization is designed for enhancing the connectivity meanwhile preserving the structure of roads. Our framework demonstrates superior performance on the DeepGlobe, Wuhan, and Massachusetts datasets.
  arXiv  Detail & Related papers  (2024-03-03T02:56:43Z)
• Raising the Bar of AI-generated Image Detection with CLIP [50.345365081177555]
  The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection strategy based on CLIP features and study its performance in a wide variety of challenging scenarios.
  arXiv  Detail & Related papers  (2023-11-30T21:11:20Z)
• Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration [59.6021678234829]
  We propose a novel method to restore the intermediate features for two sparsely sampled and adjacent video frames. With the integration of our method, the efficiency of three commonly used baselines has been improved by over 50%, with a mere 0.5% reduction in recognition accuracy.
  arXiv  Detail & Related papers  (2023-07-27T13:52:42Z)

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.