Multi-axis Analysis of Image Manipulation Localization

• URL: http://arxiv.org/abs/2605.20174v1
• Date: Tue, 19 May 2026 17:54:33 GMT
• Title: Multi-axis Analysis of Image Manipulation Localization
• Abstract summary: Manipulated images could spread misinformation, create false narratives, and influence people's opinions on important issues.<n>We introduce Analysis Under Domain-shifts, qualIty, Type, and Size (AUDITS) to study axes of analysis in image manipulation detection.<n>AUDITS comprises over 530K images from two distinct sources (user and news photos)
• Score: 29.967054752383607
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Advanced image editing software enables easy creation of highly convincing image manipulations, which has been made even more accessible in recent years due to advances in generative AI. Manipulated images, while often harmless, could spread misinformation, create false narratives, and influence people's opinions on important issues. Despite this growing threat, there is limited research on detecting advanced manipulations across different visual domains. Thus, we introduce Analysis Under Domain-shifts, qualIty, Type, and Size (AUDITS), a comprehensive benchmark designed for studying axes of analysis in image manipulation detection. AUDITS comprises over 530K images from two distinct sources (user and news photos). We curate our dataset to support analysis across multiple axes using recent diffusion-based inpaintings, spanning a diverse range of manipulation types and sizes. We conduct experiments under different types of domain shift to evaluate robustness of existing image manipulation detection methods. Our goal is to drive further research in this area by offering new insights that would help develop more reliable and generalizable image manipulation detection methods.

Related papers

• FRAME: Forensic Routing and Adaptive Multi-path Evidence Fusion for Image Manipulation Detection [3.9783598254756023]
  We present textbfFRAME, a method for textbfForensic textbfRouting and textbfAdaptive textbfMulti-path textbfEvidence fusion for image manipulation detection.<n> FRAME organizes diverse forensic algorithms into a multi-path analysis space, adaptively selects informative forensic paths for each input image, and fuses complementary evidence to improve detection and localization performance.
  arXiv  Detail & Related papers  (2026-05-12T23:48:26Z)
• ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation [81.52606410224136]
  We present textbfManipBench,' a large-scale benchmark for image manipulation detection and localization.<n>We also propose textbfManipShield,' an all-in-one model based on a Multimodal Large Language Model (MLLM) to achieve unified image manipulation detection, localization, and explanation.
  arXiv  Detail & Related papers  (2025-11-18T08:50:17Z)
• Learning Universal Features for Generalizable Image Forgery Localization [53.666188847170915]
  We present an approach for Generalizable Image Forgery localization (GIFL)<n>Our model can detect both seen and unseen forgeries, providing a more practical and efficient solution to counter false information in the era of generative AI.<n>Our method focuses on learning general features from the pristine content rather than traces of specific forgeries.
  arXiv  Detail & Related papers  (2025-04-10T05:20:29Z)
• ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection [107.86009509291581]
  We propose ForgerySleuth to perform comprehensive clue fusion and generate segmentation outputs indicating regions that are tampered with.<n>Our experiments demonstrate the effectiveness of ForgeryAnalysis and show that ForgerySleuth significantly outperforms existing methods in robustness, generalization, and explainability.
  arXiv  Detail & Related papers  (2024-11-29T04:35:18Z)
• Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors [62.63467652611788]
  We introduce SEMI-TRUTHS, featuring 27,600 real images, 223,400 masks, and 1,472,700 AI-augmented images. Each augmented image is accompanied by metadata for standardized and targeted evaluation of detector robustness. Our findings suggest that state-of-the-art detectors exhibit varying sensitivities to the types and degrees of perturbations, data distributions, and augmentation methods used.
  arXiv  Detail & Related papers  (2024-11-12T01:17:27Z)
• DA-HFNet: Progressive Fine-Grained Forgery Image Detection and Localization Based on Dual Attention [12.36906630199689]
  We construct a DA-HFNet forged image dataset guided by text or image-assisted GAN and Diffusion model. Our goal is to utilize a hierarchical progressive network to capture forged artifacts at different scales for detection and localization.
  arXiv  Detail & Related papers  (2024-06-03T16:13:33Z)
• On the exploitation of DCT statistics for cropping detectors [5.039808715733204]
  In this work, we investigated a novel image resolution classifier that employs DCT statistics with the goal to detect the original resolution of images. The results demonstrate the classifier's reliability in distinguishing between cropped and not cropped images, providing a dependable estimation of their original resolution. This work opens new perspectives in the field, with potential to transform image analysis and usage across multiple domains.
  arXiv  Detail & Related papers  (2024-03-21T19:05:31Z)
• GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning [50.7702397913573]
  The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology. We propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection.
  arXiv  Detail & Related papers  (2024-02-03T03:13:50Z)
• ObjectFormer for Image Manipulation Detection and Localization [118.89882740099137]
  We propose ObjectFormer to detect and localize image manipulations. We extract high-frequency features of the images and combine them with RGB features as multimodal patch embeddings. We conduct extensive experiments on various datasets and the results verify the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-03-28T12:27:34Z)
• Image Manipulation Detection by Multi-View Multi-Scale Supervision [11.319080833880307]
  Key challenge of image manipulation detection is how to learn generalizable features that are sensitive to manipulations in novel data. In this paper we address both aspects by multi-view feature learning and multi-scale supervision. Our thoughts are realized by a new network which we term MVSS-Net.
  arXiv  Detail & Related papers  (2021-04-14T13:05:58Z)
• Translate to Adapt: RGB-D Scene Recognition across Domains [18.40373730109694]
  In this work we put under the spotlight the existence of a possibly severe domain shift issue within multi-modality scene recognition datasets. We present a method based on self-supervised inter-modality translation able to adapt across different camera domains.
  arXiv  Detail & Related papers  (2021-03-26T18:20:29Z)

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.