Towards Explainable Fake Image Detection with Multi-Modal Large Language Models

• URL: http://arxiv.org/abs/2504.14245v1
• Date: Sat, 19 Apr 2025 09:42:25 GMT
• Title: Towards Explainable Fake Image Detection with Multi-Modal Large Language Models
• Authors: Yikun Ji, Yan Hong, Jiahui Zhan, Haoxing Chen, jun lan, Huijia Zhu, Weiqiang Wang, Liqing Zhang, Jianfu Zhang,
• Abstract summary: We argue that fake image detection should not operate as a "black box"<n>In this work, we evaluate the capabilities of MLLMs in comparison to traditional detection methods and human evaluators.<n>We propose a framework that integrates these prompts to develop a more robust, explainable, and reasoning-driven detection system.
• Score: 38.09674979670241
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Progress in image generation raises significant public security concerns. We argue that fake image detection should not operate as a "black box". Instead, an ideal approach must ensure both strong generalization and transparency. Recent progress in Multi-modal Large Language Models (MLLMs) offers new opportunities for reasoning-based AI-generated image detection. In this work, we evaluate the capabilities of MLLMs in comparison to traditional detection methods and human evaluators, highlighting their strengths and limitations. Furthermore, we design six distinct prompts and propose a framework that integrates these prompts to develop a more robust, explainable, and reasoning-driven detection system. The code is available at https://github.com/Gennadiyev/mllm-defake.

Related papers

• Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensics [18.989883830031093]
  multimodal Large Language Models (LLMs) have encoded rich world knowledge but struggle to comprehend local forgery details.<n>We propose a framework capable of evaluating image authenticity, localizing tampered regions, providing evidence, and tracing generation methods based on semantic tampering clues.<n>We conduct qualitative and quantitative experiments and show that GPT4V can achieve an accuracy of 92.1% in Autosplice and 86.3% in LaMa, which is competitive with state-of-the-art AIGC detection methods.
  arXiv  Detail & Related papers  (2025-04-16T01:02:46Z)
• Towards General Visual-Linguistic Face Forgery Detection(V2) [90.6600794602029]
  Face manipulation techniques have achieved significant advances, presenting serious challenges to security and social trust.<n>Recent works demonstrate that leveraging multimodal models can enhance the generalization and interpretability of face forgery detection.<n>We propose Face Forgery Text Generator (FFTG), a novel annotation pipeline that generates accurate text descriptions by leveraging forgery masks for initial region and type identification.
  arXiv  Detail & Related papers  (2025-02-28T04:15:36Z)
• DILLEMA: Diffusion and Large Language Models for Multi-Modal Augmentation [0.13124513975412253]
  We present a novel framework for testing vision neural networks that leverages Large Language Models and control-conditioned Diffusion Models. Our approach begins by translating images into detailed textual descriptions using a captioning model. These descriptions are then used to produce new test images through a text-to-image diffusion process.
  arXiv  Detail & Related papers  (2025-02-05T16:35:42Z)
• SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization [49.931663904599205]
  Researchers have developed techniques to develop Large Multimodal Models with In-Context Learning capabilities. Existing LMMs fail to effectively leverage the visual context in multimodal demonstrations and instead simply follow textual patterns. We propose Symbol Demonstration Direct Preference Optimization (SymDPO) to break the traditional paradigm of constructing multimodal demonstrations.
  arXiv  Detail & Related papers  (2024-11-17T08:29:14Z)
• FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models [16.737419222106308]
  FakeShield is a framework capable of evaluating image authenticity, generating tampered region masks, and providing a judgment basis based on pixel-level and image-level tampering clues.<n>In experiments, FakeShield effectively detects and localizes various tampering techniques, offering an explainable and superior solution compared to previous IFDL methods.
  arXiv  Detail & Related papers  (2024-10-03T17:59:34Z)
• Dynamic Analysis and Adaptive Discriminator for Fake News Detection [59.41431561403343]
  We propose a Dynamic Analysis and Adaptive Discriminator (DAAD) approach for fake news detection. For knowledge-based methods, we introduce the Monte Carlo Tree Search algorithm to leverage the self-reflective capabilities of large language models. For semantic-based methods, we define four typical deceit patterns to reveal the mechanisms behind fake news creation.
  arXiv  Detail & Related papers  (2024-08-20T14:13:54Z)
• FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models [62.66610648697744]
  We introduce a taxonomy of generative visual forgery concerning human perception, based on which we collect forgery descriptions in human natural language. FakeBench examines LMMs with four evaluation criteria: detection, reasoning, interpretation and fine-grained forgery analysis. This research presents a paradigm shift towards transparency for the fake image detection area.
  arXiv  Detail & Related papers  (2024-04-20T07:28:55Z)
• SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models [61.8876114116716]
  Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-related tasks.<n>However, their ability to detect subtle visual spoofing and forgery clues in face attack detection tasks remains underexplored.<n>We introduce a benchmark, SHIELD, to evaluate MLLMs for face spoofing and forgery detection.
  arXiv  Detail & Related papers  (2024-02-06T17:31:36Z)
• 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)

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.