Evidence-Guided Detection, Localization and Explanation for Text-Centric Image Forensics

• URL: http://arxiv.org/abs/2609.02097v1
• Date: Wed, 02 Sep 2026 04:37:32 GMT
• Title: Evidence-Guided Detection, Localization and Explanation for Text-Centric Image Forensics
• Abstract summary: AIGC has made text-centric image manipulation increasingly accessible.<n>This paper presents our solution to the GenText-Forensics Challenge at ACM Multimedia 2026.
• Score: 5.228601974168999
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid progress of AIGC has made text-centric image manipulation increasingly accessible, creating new forensic challenges that require not only authenticity detection but also spatial grounding and evidence-based explanation. This paper presents our solution to the GenText-Forensics Challenge at ACM Multimedia 2026. We propose an evidence-guided detector-localizer-reasoner system, where an image-level detector provides a global authenticity prior, a dedicated localizer extracts tampered regions as spatial grounding evidence, and an MLLM-based reasoner generates structured forensic reports grounded in this expert forensic evidence. These modules are connected through a cascaded evidence flow: the detector gates the subsequent localization and prompting process, the localizer converts tamper responses into grounding boxes, and the reasoner is trained to synthesize the detector decision and localized evidence into the final report. As a key part of our method, we introduce iterative difficulty-aware mining to improve localization quality and apply report-mask consistency post-processing to align report grounding with predicted masks. On the official hidden test set, our system achieves a final score of 0.638 and ranks second in the challenge, validating the effectiveness of the proposed evidence-guided system. The code is available at https://github.com/peifengLiu42/ACMMM26-evidence-guided-detector-localizer-reasoner-system.

Related papers

• From Detection to Localization: A Unified Forensics Framework for Fully Synthetic and Tampered Images [7.9180538960840385]
  This work extends an existing detector by introducing a unified multiclass framework (real vs. fully generated vs. tampered)<n>In addition to classifying image authenticity, the framework incorporates a segmentation branch to enable pixel-level localization of tampered regions.<n>The proposed approach outperforms selected recent benchmarks, offering an efficient solution with improved classification accuracy and higher IoU scores for the localization task.
  arXiv  Detail & Related papers  (2026-09-02T14:16:44Z)
• Defake-o3: From Speculative Rationales to Verifiable Evidence for Explainable AIGI Detection [8.599317072232198]
  We present Defake-o3, an AIGI detector that moves from speculative rationales to verifiable evidence.<n>It combines interactive visual search with verifier-guided evidence alignment.<n>Defake-o3 improves both detection accuracy and explanation quality.
  arXiv  Detail & Related papers  (2026-08-17T08:30:32Z)
• Explainable Deepfake Detection Challenge [42.4485282926075]
  The Explainable Deepfake Detection Challenge at ACM Multimedia 2026 is designed to benchmark this joint capability.<n>The evaluation combines classification metrics with semantic similarity, simplicity, and intent-aware grounding metrics.<n>The methodologies developed through the challenge will contribute to the development of next-generation explainable deepfake detectors.
  arXiv  Detail & Related papers  (2026-07-23T07:42:43Z)
• ForensicConcept: Transferable Forensic Concepts for AIGI Detection [81.29606528968698]
  We propose ForensicConcept, a framework that extracts explicit forensic concepts from detectors and enables their transfer across backbones.<n>Our method localizes decision-critical patches via Transformer attribution, clusters them into a compact concept codebook, and uses a concept-aligned projection to produce auditable evidence readouts.
  arXiv  Detail & Related papers  (2026-06-05T08:25:34Z)
• REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation Detection [33.33464433821003]
  Multimodal manipulation detection aims to simultaneously identify forged image--text pairs and localize tampered regions.<n>Inspired by human comparative reasoning, we reformulate this task as a reference-grounded verification problem.<n>We propose REVEAL, a framework explicitly designed for this comparative paradigm.
  arXiv  Detail & Related papers  (2026-05-27T13:24:41Z)
• Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection [53.789057575175065]
  Region-Aware Prompt Augmentation (RAPTA) and Attention-Driven Multimodal Copy Detection (ADMCD) are presented.<n>RAPTA uses an object detector to find salient regions and turn them into semantically grounded prompt variants.<n>ADMCD aggregates local patch, global semantic, and texture cues with a lightweight transformer to produce a fused representation.<n>Experiments show that RAPTA reduces overfitting while maintaining high synthesis quality, and that ADMCD reliably detects copying, outperforming single-modal metrics.
  arXiv  Detail & Related papers  (2026-03-13T15:16:27Z)
• Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations [56.816929931908824]
  We pioneer the detection of semantically-coordinated manipulations in multimodal data.<n>We propose a Retrieval-Augmented Manipulation Detection and Grounding (RamDG) framework.<n>Our framework significantly outperforms existing methods, achieving 2.06% higher detection accuracy on SAMM compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-09-16T04:18:48Z)
• Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization [49.71303998618939]
  This paper presents a novel Propose-Rectify framework that bridges semantic reasoning with forensic-specific analysis.<n>Our framework ensures that initial semantic proposals are systematically validated and enhanced through concrete technical evidence, resulting in comprehensive detection accuracy and localization precision.
  arXiv  Detail & Related papers  (2025-08-25T12:43:53Z)
• Mixture-of-Noises Enhanced Forgery-Aware Predictor for Multi-Face Manipulation Detection and Localization [52.87635234206178]
  This paper proposes a new framework, namely MoNFAP, specifically tailored for multi-face manipulation detection and localization. The framework incorporates two novel modules: the Forgery-aware Unified Predictor (FUP) Module and the Mixture-of-Noises Module (MNM)
  arXiv  Detail & Related papers  (2024-08-05T08:35:59Z)
• Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localization [30.317619885984005]
  We introduce the well-trained vision segmentation foundation model, i.e., Segment Anything Model (SAM) in face forgery detection and localization. Based on SAM, we propose the Detect Any Deepfakes (DADF) framework with the Multiscale Adapter. The proposed framework seamlessly integrates end-to-end forgery localization and detection optimization.
  arXiv  Detail & Related papers  (2023-06-29T16:25:04Z)
• Representative Forgery Mining for Fake Face Detection [52.896286647898386]
  We propose an attention-based data augmentation framework to guide detector refine and enlarge its attention. Our method tracks and occludes the Top-N sensitive facial regions, encouraging the detector to mine deeper into the regions ignored before for more representative forgery.
  arXiv  Detail & Related papers  (2021-04-14T03:24:19Z)

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.