Tell-Tale Watermarks for Explanatory Reasoning in Synthetic Media Forensics
Not on the map. Why?
Abstract (arXiv)
The rise of synthetic media has blurred the boundary between reality and fabrication under the evolving power of artificial intelligence, fueling an infodemic that erodes public trust in cyberspace. For digital imagery, a multitude of editing applications further complicates the forensic analysis, including semantic edits that alter content, photometric adjustments that recalibrate colour characteristics, and geometric projections that reshape viewpoints. Collectively, these transformations manipulate and control perceptual interpretation of digital imagery. This susceptibility calls for forensic enquiry into reconstructing the chain of events, thereby revealing deeper evidential insight into the presence or absence of criminal intent. This study seeks to address an inverse problem of tracing the underlying generation chain that gives rise to the observed synthetic media. A tell-tale watermarking system is developed for explanatory reasoning over the nature and extent of transformations across the lifecycle of synthetic media. Tell-tale watermarks are tailored to different classes of transformations, responding in a manner that is neither strictly robust nor fragile but instead interpretable. These watermarks function as reference clues that evolve under the same transformation dynamics as the carrier media, leaving interpretable traces when subjected to transformations. Explanatory reasoning is then performed to infer the most plausible account across the combinatorial parameter space of composite transformations. Experimental evaluations demonstrate the validity of tell-tale watermarking with respect to fidelity, synchronicity and traceability.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 41 of its 90 references that are in the map. First posted on arXiv 6 Sep 2025.
Builds on
41 of 90 references.
References · 41
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
- 2022Generative Adversarial Networkscited by 5,627
- 2018CBAM: Convolutional Block Attention Modulecited by 2,477
- 2022Competition-Level Code Generation with AlphaCodecited by 1,462
- 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
- 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
- 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
- 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 726
29 more
- 2023A Watermark for Large Language Modelscited by 725
- 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 632
- 2019Defending Against Neural Fake Newscited by 559
- 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
- 2019Face X-ray for More General Face Forgery Detectioncited by 470
- 2023DIRE for Diffusion-Generated Image Detectioncited by 390
- 2022A Systematic Evaluation of Large Language Models of Codecited by 363
- 2022Detecting Deepfakes with Self-Blended Imagescited by 338
- 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 304
- 2018Exposing Deep Fakes Using Inconsistent Head Posescited by 297
- 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 287
- 2018Deep Video Portraitscited by 267
- 2019Neural Voice Puppetry: Audio-driven Facial Reenactmentcited by 250
- 2020The Creation and Detection of Deepfakes: A Surveycited by 247
- 2018Do GANs leave artificial fingerprints?cited by 190
- 2018X2Face: A network for controlling face generation by using images, audio, and pose codescited by 189
- 2018Learning Rich Features for Image Manipulation Detectioncited by 154
- 2019FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signalscited by 145
- 2022TruFor: Leveraging all-round clues for trustworthy image forgery detection and localizationcited by 130
- 2016Neural Photo Editing with Introspective Adversarial Networkscited by 109
- 2023The science of fake newscited by 97
- 2020Distortion Agnostic Deep Watermarkingcited by 90
- 2021Face Forensics in the Wildcited by 87
- 2024Proactive Detection of Voice Cloning with Localized Watermarkingcited by 78
- 2018Image Provenance Analysis at Scalecited by 16
- 2023Prompt Engineering-assisted Malware Dynamic Analysis Using GPT-4cited by 7
- 2023Cyber Vaccine for Deepfake Immunitycited by 3
- 2018Beyond Pixels: Image Provenance Analysis Leveraging Metadatacited by 2
- 2025SoK: Timeline based event reconstruction for digital forensics: Terminology, methodology, and current challengescited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026Seeing Is No Longer Believing: Frontier Image Generation Models, Synthetic Visual Evidence, and Real-World Risk
- 2026Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics
- 2026From Forensics to Ecosystems: Rethinking Watermarks for Generative AI Oversight
- 2026Can You Trust What You See? Human and AI Detection of Synthetic Legal Evidence
- 2024FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models
- 2026WorldFact-Bench: Beyond Image-Internal Plausibility to Image-World Consistency
- 2026Verifiable Provenance and Watermarking for Generative AI: An Evidentiary Framework for International Operational Law and Domestic Courts
- 2026Watermark Forensics for Generative Models: An Information-Theoretic Perspective