Beyond Semantics: Uncovering the Physics of Fakes via Universal Physical Descriptors for Cross-Modal Synthetic Detection

• URL: http://arxiv.org/abs/2604.04608v1
• Date: Mon, 06 Apr 2026 11:50:29 GMT
• Title: Beyond Semantics: Uncovering the Physics of Fakes via Universal Physical Descriptors for Cross-Modal Synthetic Detection
• Abstract summary: We propose a novel feature selection algorithm that identifies five core physical features that exhibit consistent discnative power across all tested datasets.<n>Our method achieves state-of-the-art performance on multiple Genimage benchmarks, with near-perfect accuracy (99.8%) on datasets such as Wukong and SDv1.4.
• Score: 34.95491424781195
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The rapid advancement of AI generated content (AIGC) has blurred the boundaries between real and synthetic images, exposing the limitations of existing deepfake detectors that often overfit to specific generative models. This adaptability crisis calls for a fundamental reexamination of the intrinsic physical characteristics that distinguish natural from AI-generated images. In this paper, we address two critical research questions: (1) What physical features can stably and robustly discriminate AI generated images across diverse datasets and generative architectures? (2) Can these objective pixel-level features be integrated into multimodal models like CLIP to enhance detection performance while mitigating the unreliability of language-based information? To answer these questions, we conduct a comprehensive exploration of 15 physical features across more than 20 datasets generated by various GANs and diffusion models. We propose a novel feature selection algorithm that identifies five core physical features including Laplacian variance, Sobel statistics, and residual noise variance that exhibit consistent discriminative power across all tested datasets. These features are then converted into text encoded values and integrated with semantic captions to guide image text representation learning in CLIP. Extensive experiments demonstrate that our method achieves state-of-the-art performance on multiple Genimage benchmarks, with near-perfect accuracy (99.8%) on datasets such as Wukong and SDv1.4. By bridging pixel level authenticity with semantic understanding, this work pioneers the use of physically grounded features for trustworthy vision language modeling and opens new directions for mitigating hallucinations and textual inaccuracies in large multimodal models.

Related papers

• LHSDet: High-Resolution AI-Generated Image Detection via Visual Question Answering [9.47286721599147]
  We propose a novel high-resolution AI-generated image detector, termed LHSDet.<n>We formulate the AI-generated image detection task as a Visual Question Answering problem.<n>We use a fine-tuned vision-language framework to fully exploit the complementary information between visual and textual modalities.
  arXiv  Detail & Related papers  (2026-08-08T02:13:33Z)
• TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image Detection [70.42796551833946]
  incorporating texture-level artifact features alongside semantic features into multimodal large language models (MLLMs) can enhance their AIGI detection capability.<n>We propose a lightweight fusion adapter, TranX-Adapter, which integrates a Task-aware Optimal-Transport Fusion.<n>Experiments on standard AIGI detection benchmarks upon several advanced MLLMs, show that our TranX-Adapter brings consistent and significant improvements.
  arXiv  Detail & Related papers  (2026-02-25T09:22:46Z)
• Synthetic Image Detection with CLIP: Understanding and Assessing Predictive Cues [0.0]
  It is unclear whether CLIP-based detectors simply detect strong visual artifacts or exploit subtle semantic biases.<n>We analyze what CLIP-based detectors learn using an interpretable linear head with de-correlated activations and a text-grounded concept-model.
  arXiv  Detail & Related papers  (2026-02-12T20:21:32Z)
• Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios [54.07895223545793]
  This paper introduces the Real-World Robustness dataset (RRDataset) for comprehensive evaluation of detection models across three dimensions.<n>RRDataset includes high-quality images from seven major scenarios.<n>We benchmarked 17 detectors and 10 vision-language models (VLMs) on RRDataset and conducted a large-scale human study.
  arXiv  Detail & Related papers  (2025-09-11T06:15:52Z)
• NS-Net: Decoupling CLIP Semantic Information through NULL-Space for Generalizable AI-Generated Image Detection [14.7077339945096]
  NS-Net is a novel framework that decouples semantic information from CLIP's visual features, followed by contrastive learning to capture intrinsic distributional differences between real and generated images.<n>Experiments show that NS-Net outperforms existing state-of-the-art methods, achieving a 7.4% improvement in detection accuracy.
  arXiv  Detail & Related papers  (2025-08-02T07:58:15Z)
• Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection [24.512663807403186]
  InfoFD is a text-guided AI-generated image detection framework.<n>We introduce two key components: the Text-Guided Conditional Information Bottleneck (TGCIB) and Dynamic Text Orthogonalization (DTO)<n>Our model achieves exceptional generalization performance on the GenImage dataset and latest generative models.
  arXiv  Detail & Related papers  (2025-05-21T07:46:26Z)
• FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensics [66.14786900470158]
  We propose FakeScope, an expert multimodal model (LMM) tailored for AI-generated image forensics.<n>FakeScope identifies AI-synthetic images with high accuracy and provides rich, interpretable, and query-driven forensic insights.<n>FakeScope achieves state-of-the-art performance in both closed-ended and open-ended forensic scenarios.
  arXiv  Detail & Related papers  (2025-03-31T16:12:48Z)
• CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI [58.35348718345307]
  Current efforts to distinguish between real and AI-generated images may lack generalization.<n>We propose a novel framework, Co-Spy, that first enhances existing semantic features.<n>We also create Co-Spy-Bench, a comprehensive dataset comprising 5 real image datasets and 22 state-of-the-art generative models.
  arXiv  Detail & Related papers  (2025-03-24T01:59:29Z)
• D-Judge: How Far Are We? Assessing the Discrepancies Between AI-synthesized and Natural Images through Multimodal Guidance [19.760989919485894]
  We construct a large-scale multimodal dataset, D-ANI, comprising 5,000 natural images and over 440,000 AIGI samples.<n>We then introduce an AI-Natural Image Discrepancy assessment benchmark (D-Judge) to address the critical question: how far are AI-generated images (AIGIs) from truly realistic images?
  arXiv  Detail & Related papers  (2024-12-23T15:08:08Z)
• Multi-Modal Prompt Learning on Blind Image Quality Assessment [65.0676908930946]
  Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. This paper introduces an innovative multi-modal prompt-based methodology for IQA.
  arXiv  Detail & Related papers  (2024-04-23T11:45:32Z)
• Parents and Children: Distinguishing Multimodal DeepFakes from Natural Images [60.34381768479834]
  Recent advancements in diffusion models have enabled the generation of realistic deepfakes from textual prompts in natural language. We pioneer a systematic study on deepfake detection generated by state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2023-04-02T10:25:09Z)

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.