Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics

• URL: http://arxiv.org/abs/2609.02268v1
• Date: Wed, 02 Sep 2026 08:15:52 GMT
• Title: Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics
• Abstract summary: We propose a self-referential retrosynthesis framework for explainable AI provenance under a fixed-generator setting.<n>We use a jointly optimized encoder-decoder pair to implement a self-embedding mechanism that enables round-trip consistency verification.<n>Our approach eliminates the need for watermark embedding or modifications to the generation process.
• Score: 28.375184021885
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rapid proliferation of generative models on Machine Learning as a Service (MLaaS) platforms, reliably tracing the provenance of synthetic media without modifying generator architectures or parameters remains a major challenge. In this work, we propose a self-referential retrosynthesis framework for explainable AI provenance forensics under a fixed-generator setting. The framework leverages a jointly optimized encoder-decoder pair to implement a self-embedding mechanism that enables round-trip consistency verification. During inference, client inputs are first encoded and then processed by the generator to produce outputs with high visual fidelity. For forensic verification, the consistency between the resynthesized image and the query image is analyzed to determine whether the image originates from the target generative model. Our approach eliminates the need for watermark embedding or modifications to the generation process. Experimental results show that images generated from encoded inputs maintain visual quality comparable to original generator outputs, while decoded images reliably trace back to their corresponding source inputs. Furthermore, the framework provides interpretable evidence for generative content provenance, establishing a practical tool for explainable generative AI forensics.

Related papers

• Can Vision-Language Models Reason about AI Edits in Images? [78.04125956307838]
  Vision-Language Models (VLMs) offer a promising alternative due to their strong visual understanding and reasoning capabilities.<n>We propose a GRPO-based training framework that utilizes simple accuracy and format rewards.<n>Our approach achieves competitive detection and localization performance compared to state-of-the-art image forgery detectors.
  arXiv  Detail & Related papers  (2026-07-30T16:23:40Z)
• EchoGen: Generating Visual Echoes in Any Scene via Feed-Forward Subject-Driven Auto-Regressive Model [56.53617289548353]
  EchoGen is a pioneering framework that empowers Visual Auto-Regressive ( VAR) models with subject-driven generation capabilities.<n>We employ a semantic encoder to extract the subject's abstract identity, which is injected through decoupled cross-attention to guide the overall composition.<n>To the best of our knowledge, EchoGen is the first feed-forward subject-driven framework built upon VAR models.
  arXiv  Detail & Related papers  (2025-09-30T11:45:48Z)
• OmniDFA: A Unified Framework for Open Set Synthesis Image Detection and Few-Shot Attribution [21.62979058692505]
  OmniDFA is a novel framework for AIGI that assesses the authenticity of images, and determines the origins in a few-shot manner.<n>We construct OmniFake, a large class-aware synthetic image dataset that curates $1.17$ M images from $45$ distinct generative models.<n>Experiments demonstrate that OmniDFA exhibits excellent capability in open-set attribution and achieves state-of-the-art generalization performance on AIGI detection.
  arXiv  Detail & Related papers  (2025-09-30T02:36:40Z)
• Semantic-Aware Reconstruction Error for Detecting AI-Generated Images [22.83053631078616]
  We propose a novel representation, namely Semantic-Aware Reconstruction Error (SARE), that measures the semantic difference between an image and its caption-guided reconstruction.<n>SARE provides a robust and discriminative feature for detecting fake images across diverse generative models.<n>We also introduce a fusion module that integrates SARE into the backbone detector via a cross-attention mechanism.
  arXiv  Detail & Related papers  (2025-08-13T04:37:36Z)
• A Watermark for Auto-Regressive Image Generation Models [50.599325258178254]
  We propose C-reweight, a distortion-free watermarking method explicitly designed for image generation models.<n>C-reweight mitigates retokenization mismatch while preserving image fidelity.
  arXiv  Detail & Related papers  (2025-06-13T00:15:54Z)
• Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images [8.167678851224121]
  Traditional methods fail to generalize to unseen generators due to reliance on features specific to known sources during training.<n>We propose a novel approach that explicitly models forensic microstructures.<n>This self-description enables us to perform zero-shot detection of synthetic images, open-set source attribution of images, and clustering based on source without prior knowledge.
  arXiv  Detail & Related papers  (2025-03-26T21:34:37Z)
• Time Step Generating: A Universal Synthesized Deepfake Image Detector [0.4488895231267077]
  We propose a universal synthetic image detector Time Step Generating (TSG) TSG does not rely on pre-trained models' reconstructing ability, specific datasets, or sampling algorithms. We test the proposed TSG on the large-scale GenImage benchmark and it achieves significant improvements in both accuracy and generalizability.
  arXiv  Detail & Related papers  (2024-11-17T09:39:50Z)
• Epsilon-VAE: Denoising as Visual Decoding [61.29255979767292]
  We propose denoising as decoding, shifting from single-step reconstruction to iterative refinement.<n>Specifically, we replace the decoder with a diffusion process that iteratively refines noise to recover the original image.<n>By adopting iterative reconstruction through diffusion, our autoencoder, namely Epsilon-VAE, achieves high reconstruction quality.
  arXiv  Detail & Related papers  (2024-10-05T08:27:53Z)
• BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution [20.85450451277421]
  Synthetic image attribution addresses the problem of tracing back the origin of images produced by generative models.<n>We propose a framework for open set attribution of synthetic images, named BOSC, that relies on the concept of backdoor attacks.
  arXiv  Detail & Related papers  (2024-05-19T09:17:43Z)
• LCM-Lookahead for Encoder-based Text-to-Image Personalization [82.56471486184252]
  We explore the potential of using shortcut-mechanisms to guide the personalization of text-to-image models. We focus on encoder-based personalization approaches, and demonstrate that by tuning them with a lookahead identity loss, we can achieve higher identity fidelity.
  arXiv  Detail & Related papers  (2024-04-04T17:43:06Z)
• 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)
• Ensembling with Deep Generative Views [72.70801582346344]
  generative models can synthesize "views" of artificial images that mimic real-world variations, such as changes in color or pose. Here, we investigate whether such views can be applied to real images to benefit downstream analysis tasks such as image classification. We use StyleGAN2 as the source of generative augmentations and investigate this setup on classification tasks involving facial attributes, cat faces, and cars.
  arXiv  Detail & Related papers  (2021-04-29T17:58:35Z)

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.