Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection

• URL: http://arxiv.org/abs/2603.10598v1
• Date: Wed, 11 Mar 2026 09:53:06 GMT
• Title: Layer Consistency Matters: Elegant Latent Transition Discrepancy for Generalizable Synthetic Image Detection
• Abstract summary: Real images maintain consistent semantic attention and structural coherence in their latent representations, whereas synthetic ones present discernible patterns.<n>We propose a novel approach termed latent transition discrepancy (LTD), which captures the inter-layer consistency differences of real and synthetic images.<n>Our approach exceeds the base model by 14.35% in mean Acc across three datasets containing diverse GANs and DMs.
• Score: 15.935593506859043
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent rapid advancement of generative models has significantly improved the fidelity and accessibility of AI-generated synthetic images. While enabling various innovative applications, the unprecedented realism of these synthetics makes them increasingly indistinguishable from authentic photographs, posing serious security risks, such as media credibility and content manipulation. Although extensive efforts have been dedicated to detecting synthetic images, most existing approaches suffer from poor generalization to unseen data due to their reliance on model-specific artifacts or low-level statistical cues. In this work, we identify a previously unexplored distinction that real images maintain consistent semantic attention and structural coherence in their latent representations, exhibiting more stable feature transitions across network layers, whereas synthetic ones present discernible distinct patterns. Therefore, we propose a novel approach termed latent transition discrepancy (LTD), which captures the inter-layer consistency differences of real and synthetic images. LTD adaptively identifies the most discriminative layers and assesses the transition discrepancies across layers. Benefiting from the proposed inter-layer discriminative modeling, our approach exceeds the base model by 14.35\% in mean Acc across three datasets containing diverse GANs and DMs. Extensive experiments demonstrate that LTD outperforms recent state-of-the-art methods, achieving superior detection accuracy, generalizability, and robustness. The code is available at https://github.com/yywencs/LTD

Related papers

• Rarity-Aware Discrete Diffusion with Spatially Consistent Decoding for Photo-Realistic Image Super-Resolution [80.28905986756685]
  DiMOO-SR is a rarity-aware multimodal discrete diffusion framework for photo-realistic image Super-Resolution.<n>Experiments on widely used real-world SR benchmarks demonstrate that DiMOO-SR achieves competitive perceptual quality with only a few parallel decoding steps.
  arXiv  Detail & Related papers  (2026-07-20T07:01:01Z)
• What Makes Synthetic Data Effective in Image Segmentation [35.90116236392466]
  Synthetic data has emerged as a promising solution for visual understanding.<n>In this work, we conduct a systematic analysis of synthetic images from state-of-the-art diffusion models to uncover the factors governing their utility.<n>We propose SENSE, a unified framework that leverages flexible and scalable synthetic data to substantially enhance segmentation performance.
  arXiv  Detail & Related papers  (2026-05-19T03:07:04Z)
• 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)
• INSIGHT: An Interpretable Neural Vision-Language Framework for Reasoning of Generative Artifacts [0.0]
  Current forensic systems degrade sharply under real-world conditions.<n>Most detectors operate as opaques, offering little insight into why an image is flagged as synthetic.<n>We introduce INSIGHT, a unified framework for robust detection and transparent explanation of AI-generated images.
  arXiv  Detail & Related papers  (2025-11-27T11:43:50Z)
• Explainable Synthetic Image Detection through Diffusion Timestep Ensembling [30.298198387824275]
  We propose a novel synthetic image detection method that directly utilizes features of intermediately noised images by training an ensemble on multiple noised timesteps.<n>To enhance human comprehension, we introduce a metric-grounded explanation generation and refinement module.<n>Our method achieves state-of-the-art performance with 98.91% and 95.89% detection accuracy on regular and challenging samples respectively.
  arXiv  Detail & Related papers  (2025-03-08T13:04:20Z)
• SFLD: Reducing the content bias for AI-generated Image Detection [23.152346805893373]
  A novel approach, SFLD, incorporates PatchShuffle to integrate high-level semantic and low-level textural information.<n>Current benchmarks face challenges such as low image quality, insufficient content preservation, and limited class diversity.<n>In response, we introduce Twin Synths, a new benchmark generation methodology that constructs visually near-identical pairs of real and synthetic images.
  arXiv  Detail & Related papers  (2025-02-24T12:38:34Z)
• StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model [62.25424831998405]
  StealthDiffusion is a framework that modifies AI-generated images into high-quality, imperceptible adversarial examples. It is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries.
  arXiv  Detail & Related papers  (2024-08-11T01:22:29Z)
• Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization [62.157627519792946]
  We introduce a novel framework called bridged transfer, which initially employs synthetic images for fine-tuning a pre-trained model to improve its transferability. We propose dataset style inversion strategy to improve the stylistic alignment between synthetic and real images. Our proposed methods are evaluated across 10 different datasets and 5 distinct models, demonstrating consistent improvements.
  arXiv  Detail & Related papers  (2024-03-28T22:25:05Z)
• Generalizable Synthetic Image Detection via Language-guided Contrastive Learning [22.533225521726116]
  malevolent use of synthetic images, such as the dissemination of fake news or the creation of fake profiles, raises significant concerns regarding the authenticity of images.<n>We propose a simple yet very effective synthetic image detection method via a language-guided contrastive learning.<n>It is shown that our proposed LanguAge-guided SynThEsis Detection (LASTED) model achieves much improved generalizability to unseen image generation models.
  arXiv  Detail & Related papers  (2023-05-23T08:13:27Z)
• Bridging Synthetic and Real Images: a Transferable and Multiple Consistency aided Fundus Image Enhancement Framework [61.74188977009786]
  We propose an end-to-end optimized teacher-student framework to simultaneously conduct image enhancement and domain adaptation. We also propose a novel multi-stage multi-attention guided enhancement network (MAGE-Net) as the backbones of our teacher and student network.
  arXiv  Detail & Related papers  (2023-02-23T06:16:15Z)
• Semantic Image Synthesis via Diffusion Models [174.24523061460704]
  Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks.<n>Recent work on semantic image synthesis mainly follows the de facto GAN-based approaches.<n>We propose a novel framework based on DDPM for semantic image synthesis.
  arXiv  Detail & Related papers  (2022-06-30T18:31:51Z)
• You Only Need Adversarial Supervision for Semantic Image Synthesis [84.83711654797342]
  We propose a novel, simplified GAN model, which needs only adversarial supervision to achieve high quality results. We show that images synthesized by our model are more diverse and follow the color and texture of real images more closely.
  arXiv  Detail & Related papers  (2020-12-08T23:00:48Z)

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.