Who Made This? Fake Detection and Source Attribution with Diffusion Features

• URL: http://arxiv.org/abs/2510.27602v1
• Date: Fri, 31 Oct 2025 16:27:34 GMT
• Title: Who Made This? Fake Detection and Source Attribution with Diffusion Features
• Authors: Simone Bonechi, Paolo Andreini, Barbara Toniella Corradini,
• Abstract summary: We introduce FRIDA, a framework for deepfake detection and source attribution.<n>A compact neural model enables accurate source attribution.<n>Results show that diffusion representations inherently encode generator-specific patterns.
• Score: 0.15293427903448018
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The rapid progress of generative diffusion models has enabled the creation of synthetic images that are increasingly difficult to distinguish from real ones, raising concerns about authenticity, copyright, and misinformation. Existing supervised detectors often struggle to generalize across unseen generators, requiring extensive labeled data and frequent retraining. We introduce FRIDA (Fake-image Recognition and source Identification via Diffusion-features Analysis), a lightweight framework that leverages internal activations from a pre-trained diffusion model for deepfake detection and source generator attribution. A k-nearest-neighbor classifier applied to diffusion features achieves state-of-the-art cross-generator performance without fine-tuning, while a compact neural model enables accurate source attribution. These results show that diffusion representations inherently encode generator-specific patterns, providing a simple and interpretable foundation for synthetic image forensics.

Related papers

• Detecting AI-Generated Images via Diffusion Snap-Back Reconstruction: A Forensic Approach [0.0]
  Traditional deepfake detection methods fail against text-to-image systems such as Stable Diffusion and DALL-E.<n>This paper introduces a diffusion-based forensic framework that leverages multi-strength image reconstruction dynamics.
  arXiv  Detail & Related papers  (2025-11-01T01:35:54Z)
• $\bf{D^3}$QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection [85.9202830503973]
  Visual autoregressive (AR) models generate images through discrete token prediction.<n>We propose to leverage Discrete Distribution Discrepancy-aware Quantization Error (D$3$QE) for autoregressive-generated image detection.
  arXiv  Detail & Related papers  (2025-10-07T13:02:27Z)
• LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detection [13.576997219135992]
  LATent Trajectory Embedding is a novel approach that models the evolution of latent embeddings across multiple denoising steps.<n> Experiments on several benchmarks, such as GenImage, Chameleon, and Diffusion Forensics, show that LATTE achieves superior performance.
  arXiv  Detail & Related papers  (2025-07-03T12:53:47Z)
• 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)
• DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion [94.46904504076124]
  Deepfake technology has made face swapping highly realistic, raising concerns about the malicious use of fabricated facial content. Existing methods often struggle to generalize to unseen domains due to the diverse nature of facial manipulations. We introduce DiffusionFake, a novel framework that reverses the generative process of face forgeries to enhance the generalization of detection models.
  arXiv  Detail & Related papers  (2024-10-06T06:22:43Z)
• 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)
• Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection [86.97062579515833]
  We introduce the concept of Neighboring Pixel Relationships(NPR) as a means to capture and characterize the generalized structural artifacts stemming from up-sampling operations. A comprehensive analysis is conducted on an open-world dataset, comprising samples generated by tft28 distinct generative models. This analysis culminates in the establishment of a novel state-of-the-art performance, showcasing a remarkable tft11.6% improvement over existing methods.
  arXiv  Detail & Related papers  (2023-12-16T14:27:06Z)
• Diffusion Noise Feature: Accurate and Fast Generated Image Detection [23.923353960316618]
  We propose a novel representation, Diffusion Noise Feature (DNF)<n>DNF amplifies subtle, high-frequency artifacts that act as fingerprints of artificial generation.<n>Our approach achieves remarkable accuracy, robustness, and generalization in detecting generated images.
  arXiv  Detail & Related papers  (2023-12-05T10:01:11Z)
• 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)
• DIRE for Diffusion-Generated Image Detection [128.95822613047298]
  We propose a novel representation called DIffusion Reconstruction Error (DIRE) DIRE measures the error between an input image and its reconstruction counterpart by a pre-trained diffusion model. It provides a hint that DIRE can serve as a bridge to distinguish generated and real images.
  arXiv  Detail & Related papers  (2023-03-16T13:15:03Z)

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.