Can Image Splicing and Copy-Move Forgery Be Detected by the Same Model? Forensim: An Attention-Based State-Space Approach

2026-02-10

AI Summary

Existing methods struggle to simultaneously and accurately localize both source and target regions in image splicing and copy-move forgery, often leading to semantic misinterpretation. To address this challenge, this work proposes Forensim—a novel attention-based visual state space model that, for the first time, enables joint end-to-end localization of pristine, source, and target regions within a unified architecture. By leveraging patch-wise regional attention and normalized attention maps, Forensim effectively captures internal repetitive patterns and discriminates manipulated areas. Extensive experiments demonstrate that Forensim achieves state-of-the-art performance on standard benchmarks. Furthermore, the authors introduce CMFD-Anything, a new dataset designed to address the scarcity of diverse and comprehensive copy-move forgery data in current research.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Cyber-crime defenses and forensics
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

We introduce Forensim, an attention-based state-space framework for image forgery detection that jointly localizes both manipulated (target) and source regions. Unlike traditional approaches that rely solely on artifact cues to detect spliced or forged areas, Forensim is designed to capture duplication patterns crucial for understanding context. In scenarios such as protest imagery, detecting only the forged region, for example a duplicated act of violence inserted into a peaceful crowd, can mislead interpretation, highlighting the need for joint source-target localization. Forensim outputs three-class masks (pristine, source, target) and supports detection of both splicing and copy-move forgeries within a unified architecture. We propose a visual state-space model that leverages normalized attention maps to identify internal similarities, paired with a region-based block attention module to distinguish manipulated regions. This design enables end-to-end training and precise localization. Forensim achieves state-of-the-art performance on standard benchmarks. We also release CMFD-Anything, a new dataset addressing limitations of existing copy-move forgery datasets.

Problem

• image splicing
• copy-move forgery
• source-target localization
• image manipulation detection
• forgery detection

Innovation

• image forgery detection
• state-space model
• attention mechanism
• copy-move forgery
• splicing detection