ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection

• URL: http://arxiv.org/abs/2411.19466v1
• Date: Fri, 29 Nov 2024 04:35:18 GMT
• Title: ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
• Authors: Zhihao Sun, Haoran Jiang, Haoran Chen, Yixin Cao, Xipeng Qiu, Zuxuan Wu, Yu-Gang Jiang,
• Abstract summary: We propose ForgerySleuth to perform comprehensive clue fusion and generate segmentation outputs indicating regions that are tampered with. Our experiments demonstrate the effectiveness of ForgeryAnalysis and show that ForgerySleuth significantly outperforms existing methods in robustness, generalization, and explainability.
• Score: 107.86009509291581
• License:
• Abstract: Multimodal large language models have unlocked new possibilities for various multimodal tasks. However, their potential in image manipulation detection remains unexplored. When directly applied to the IMD task, M-LLMs often produce reasoning texts that suffer from hallucinations and overthinking. To address this, in this work, we propose ForgerySleuth, which leverages M-LLMs to perform comprehensive clue fusion and generate segmentation outputs indicating specific regions that are tampered with. Moreover, we construct the ForgeryAnalysis dataset through the Chain-of-Clues prompt, which includes analysis and reasoning text to upgrade the image manipulation detection task. A data engine is also introduced to build a larger-scale dataset for the pre-training phase. Our extensive experiments demonstrate the effectiveness of ForgeryAnalysis and show that ForgerySleuth significantly outperforms existing methods in generalization, robustness, and explainability.

Related papers

• Towards Text-Image Interleaved Retrieval [49.96332254241075]
  We introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences. We construct a TIIR benchmark based on naturally interleaved wikiHow tutorials, where a specific pipeline is designed to generate interleaved queries. We propose a novel Matryoshka Multimodal Embedder (MME), which compresses the number of visual tokens at different granularity.
  arXiv  Detail & Related papers  (2025-02-18T12:00:47Z)
• A Large-scale Interpretable Multi-modality Benchmark for Facial Image Forgery Localization [22.725542948364357]
  We argue that the basic binary forgery mask is inadequate for explaining model predictions. In this study, we generate salient region-focused interpretation for the forgery images. We develop ForgeryTalker, an architecture designed for concurrent forgery localization and interpretation.
  arXiv  Detail & Related papers  (2024-12-27T15:23:39Z)
• ForgeryGPT: Multimodal Large Language Model For Explainable Image Forgery Detection and Localization [49.12958154544838]
  ForgeryGPT is a novel framework that advances the Image Forgery Detection and localization task. It captures high-order correlations of forged images from diverse linguistic feature spaces. It enables explainable generation and interactive dialogue through a newly customized Large Language Model (LLM) architecture.
  arXiv  Detail & Related papers  (2024-10-14T07:56:51Z)
• Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning [53.00683059396803]
  Mask image model (MIM) has been widely used due to its simplicity and effectiveness in recovering original information from masked images. We propose a decision-based MIM that utilizes reinforcement learning (RL) to automatically search for optimal image masking ratio and masking strategy. Our approach has a significant advantage over alternative self-supervised methods on the task of neuron segmentation.
  arXiv  Detail & Related papers  (2023-10-06T10:40:46Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• MSMG-Net: Multi-scale Multi-grained Supervised Metworks for Multi-task Image Manipulation Detection and Localization [1.14219428942199]
  A novel multi-scale multi-grained deep network (MSMG-Net) is proposed to automatically identify manipulated regions. In our MSMG-Net, a parallel multi-scale feature extraction structure is used to extract multi-scale features. The MSMG-Net can effectively perceive the object-level semantics and encode the edge artifact.
  arXiv  Detail & Related papers  (2022-11-06T14:58:21Z)

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.