paper-with-me

홈 › Papers

SynthID-Image: Image watermarking at internet scale

2025-10-10 · Sven Gowal, Rudy Bunel, Florian Stimberg, David Stutz, Guillermo Ortiz-Jimenez, Christina Kouridi, Mel Vecerik, Jamie Hayes, Sylvestre-Alvise Rebuffi, Paul Bernard, Chris Gamble, Miklós Z. Horváth, Fabian Kaczmarczyck, Alex Kaskasoli, Aleksandar Petrov, Ilia Shumailov, Meghana Thotakuri, Olivia Wiles, Jessica Yung, Zahra Ahmed, Victor Martin, Simon Rosen, Christopher Savčak, Armin Senoner, Nidhi Vyas, Pushmeet Kohli arxiv

We introduce SynthID-Image, a deep learning-based system for invisibly watermarking AI-generated imagery. This paper documents the technical desiderata, threat models, and practical challenges of deploying such a system at internet scale, addressing key requirements of effectiveness, fidelity, robustness, and security. SynthID-Image has been used to watermark over ten billion images and video frames across Google's services and its corresponding verification service is available to trusted testers. For completeness, we present an experimental evaluation of an external model variant, SynthID-O, which is available through partnerships. We benchmark SynthID-O against other post-hoc watermarking methods from the literature, demonstrating state-of-the-art performance in both visual quality and robustness to common image perturbations. While this work centers on visual media, the conclusions on deployment, constraints, and threat modeling generalize to other modalities, including audio. This paper provides a comprehensive documentation for the large-scale deployment of deep learning-based media provenance systems.

📄 PDF Abstract BibTeX arXiv:2510.09263

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Robustness Assessment and Enhancement of Text Watermarking for Google's SynthID

2025-08-27 · Xia Han, Qi Li, Jianbing Ni, Mohammad Zulkernine arxiv

Recent advances in LLM watermarking methods such as SynthID-Text by Google DeepMind offer promising solutions for tracing the provenance of AI-generated text. However, our robustness assessment reveals that SynthID-Text …

Information Retrieval

On Google's SynthID-Text LLM Watermarking System: Theoretical Analysis and Empirical Validation

2026-03-03 · Romina Omidi, Yun Dong, Binghui Wang arxiv

Google's SynthID-Text, the first ever production-ready generative watermark system for large language model, designs a novel Tournament-based method that achieves the state-of-the-art detectability for identifying AI-gen…

Watermarks Without Verification: AI Text Watermarking After the EU AI Act

2026-09-09 · Alexander Nemecek, Vipin Chaudhary, Erman Ayday arxiv

On August 2, 2026, the obligations of Article 50 of the EU AI Act took effect, requiring generative AI providers to mark the content their systems produce and ensure it can be detected as AI-generated. Days later, Anthro…

AI Watermark Evidence Fails Forensic Readiness: An Empirical Evaluation

2026-07-17 · Saifur Rahman Tamim, Amir Labib Khan arxiv

Governments are increasingly mandating that LLM-generated content carry watermarks. The EU AI Act calls for markings that are "sufficiently reliable and robust." California's SB 942 requires disclosure that is "permanent…

Adaptive Blind Watermarking Using Psychovisual Image Features

2022-12-25 · Arezoo PariZanganeh, Ghazaleh Ghorbanzadeh, Zahra Nabizadeh ShahreBabak, Nader Karimi 외

With the growth of editing and sharing images through the internet, the importance of protecting the images' authorship has increased. Robust watermarking is a known approach to maintaining copyright protection. Robustne…