ACM Multimedia 2026 · Tutorial 5 · Half-Day · In Person & on Zoom

Foundations and Frontiers
of Watermarking

Algorithms · Multimodal Extensions · Benchmarks · Authenticity Frameworks

Date
Time
2:00 – 6:00 PM · BRT (UTC−3)
Room
Bora-Bora I
Venue
Windsor Convention & Expo Center, Rio de Janeiro

Join online Zoom · Meeting ID 996 0647 6355 · Passcode 203727

Adobe Meta University of Siena University of Maryland

Overview

Invisible watermarking has re-emerged as core infrastructure for trustworthy generative AI, enabling content attribution, provenance, and responsible deployment at scale. This half-day tutorial offers a unified, end-to-end view of the field — from classical signal-processing foundations and modern learned watermarking to rigorous robustness benchmarking, downstream applications, and live demonstrations of deployed authenticity systems.

Fundamental questions remain open: capacity–robustness limits are not fully understood, generative removal attacks can erase many existing schemes, and interoperability across independently deployed systems is still unsolved. This is the second edition of the tutorial, following CVPR 2026, redesigned to be more focused and more interactive.

What you will learn

  • How deployed authenticity systems work in practice — C2PA Content Credentials, invisible watermarks that survive platform re-encoding, and the coexistence of watermarks from different providers.
  • How to evaluate robustness rigorously — calibrated detection, explicit threat models, and stress tests that span distortion, regeneration, and adversarial attacks.
  • What classical watermarking still teaches us — the imperceptibility / robustness / payload trade-off, perceptual modeling, and informed embedding as communication with side information.
  • How modern post-hoc image watermarking is built and trained — encoder–decoder architectures, perceptual losses, augmentations, and adversarial-only training — in a live, hands-on notebook.
  • How proactive schemes extend watermarking to attribution, ownership verification, privacy, and model protection across text, audio, diffusion models, and 3D.

Who should attend

Researchers, graduate students, and practitioners in multimedia, computer vision, security, and trustworthy AI. Familiarity with deep-learning fundamentals is assumed; no prior background in watermarking is required. To follow the hands-on session, bring a laptop — the notebook runs in Google Colab.

New for ACM MM 2026

A more interactive format

Building on audience feedback from the CVPR 2026 edition, we trimmed lecture material to make room for demonstrations, hands-on work, and discussion.

Live demos

Deployed systems, end to end

Attach Content Credentials, inspect them with independent tools, and recover an invisible watermark from AI-generated video after a round trip through a public video platform.

Hands-on

Colab notebook

Embed and extract payloads on your own images, measure imperceptibility, and stress-test robustness during the post-hoc watermarking session.

Open the notebook ↗

Discussion

Two panel discussions

A 30-minute panel closes the first half of the afternoon and a 25-minute panel closes the second, so questions can be raised while each topic is still fresh — instead of a single Q&A at the end.

Focus

Less overlap between talks

Each session owns a distinct part of the field: deployment, evaluation, foundations, post-hoc practice, and applications.

Venue & Date

Conference

ACM Multimedia 2026

Programme slot

Tutorial 5

Date

Saturday, November 14, 2026

Time

2:00 – 6:00 PM · BRT (UTC−3)

Room

Bora-Bora I

Format

In person + Zoom

Windsor Convention & Expo Center · R. Martinho de Mesquita, 129 – Barra da Tijuca, Rio de Janeiro – RJ, 22620-220, Brazil.

Join on Zoom: msu.zoom.us/j/99606476355 · Meeting ID 996 0647 6355 · Passcode 203727

Date, time, and room follow the official ACM MM 2026 programme — please check it for any last-minute changes. Registration is handled by the conference.

Schedule

All times are local to Rio de Janeiro (BRT, UTC−3). Each talk ends with five minutes of Q&A; Talk 3 has ten.

  1. Part I · Deployment & evaluation
  2. – 5 min

    Opening

    Opening Remarks

    Dr. Vishal Asnani · Adobe Research

    Tutorial overview, the evolution of watermarking, and why generative AI, media provenance, regulation, and attribution make it urgent now.

  3. – 30 min + 5 min Q&A

    Talk 1 · Live demos

    C2PA, Content Credentials, and Real-World Durability

    Dr. Shruti Agarwal · Adobe Research

    Live demonstrations of deployed authenticity systems used by major technology platforms. The session traces verifiable provenance metadata from creation through inspection, shows how invisible watermarks persist across common internet transformations, and explores how multiple watermarking schemes from different providers can coexist and be discovered by independent verification platforms. Follow along in the three-pillar Colab notebook and the SynthID Detector demo.

  4. – 30 min + 5 min Q&A

    Talk 2

    Benchmarking Watermark Robustness with WAVES

    Prof. Furong Huang · University of Maryland

    A rigorous framework for testing whether image watermarks survive realistic attacks without an unacceptable loss of image quality. Using the WAVES benchmark and lessons from the NeurIPS “Erasing the Invisible” competition, attendees compare distortion, regeneration, and adversarial attacks; examine beige-box and black-box threat models; and learn why adaptive stress testing is essential for building deployable watermarking systems.

  5. – 30 min

    Panel I

    Panel Discussion: Deployment & Robustness

    All speakers

    Open Q&A on real-world provenance, durability, and interoperability — and on how watermark robustness should be measured.

  6. – · Coffee break (conference coffee service · Europa, ground floor)
  7. Part II · Foundations, practice & applications
  8. – 25 min + 10 min Q&A

    Talk 3

    Watermarking Before and After Deep Learning

    Prof. Mauro Barni & Prof. Benedetta Tondi · University of Siena

    Extended Q&A: Prof. Barni can't join Panel II, so questions for him are taken here.

    Many of the questions facing modern watermarking are far from new. This talk revisits how the field matured from early empirical schemes into a theoretical framework — the imperceptibility, robustness, and payload trade-off, perceptual modeling, benchmarking, and informed watermarking as communication with side information — and asks what learning-based methods really change, from geometric robustness and desynchronization to payload and perceptual quality.

  9. – 30 min + 5 min Q&A

    Talk 4 · Hands-on

    Post-Hoc Image Watermarking in Practice

    Dr. Pierre Fernandez · Meta FAIR

    Modern learned image watermarking, from HiDDeN to TrustMark, Pixel Seal, and SynthID, and its key trade-offs in capacity, robustness, and imperceptibility. Includes a live demo and a Colab notebook in which attendees embed, reveal, and stress-test watermarks on their own images.

  10. – 25 min + 5 min Q&A

    Talk 5

    Downstream Applications and Proactive Watermarking

    Dr. Vishal Asnani · Adobe Research

    A unified taxonomy of proactive schemes — signals deliberately embedded into media and models for attribution, ownership verification, privacy protection, and generative-model control — traced across text and LLMs, audio, model protection, diffusion models, and 3D, and connected to real-world content provenance pipelines.

  11. – 25 min

    Panel II · Closing

    Panel Discussion: Methods, Applications & Open Challenges

    All speakers except Prof. Barni · closing remarks by Dr. Vishal Asnani

    Open Q&A on classical versus learned watermarking, generative-AI watermarking, the limits of robustness, and emerging applications — followed by a short summary of the afternoon and pointers to slides and resources.

Speakers & Organizers

A multi-institution team spanning industry research labs and academia.

Dr. Vishal Asnani

Dr. Vishal Asnani

Research Scientist · Adobe Research

Vishal is a Research Scientist at Adobe Research in the Cross-modal Representation Learning (XRL) team in San Jose, working on Content Authenticity and Responsible AI — including watermarking and durable content credentials for video. He earned his PhD at Michigan State University, advised by Prof. Xiaoming Liu.

Dr. Shruti Agarwal

Dr. Shruti Agarwal

Research Scientist · Adobe Research

Shruti is a Research Scientist on the AI for Content Authenticity team at Adobe. Her work centers on content provenance and multimedia forensics — spanning watermarking, deepfake detection, and robust image fingerprinting. She was previously a postdoc at MIT CSAIL with Prof. Bill Freeman and earned her PhD at UC Berkeley with Prof. Hany Farid.

Prof. Furong Huang

Prof. Furong Huang

Associate Professor · University of Maryland

Furong is an Associate Professor in the Department of Computer Science at the University of Maryland, affiliated with UMIACS, the Maryland Robotics Center, AMSC, and ECE. Her research bridges trustworthy machine learning, sequential decision-making, and generative AI, with contributions to systematic stress-testing of watermark robustness.

Prof. Mauro Barni

Prof. Mauro Barni

Full Professor · University of Siena

Mauro is a Full Professor at the Department of Information Engineering and Mathematics, University of Siena, where he leads the Visual Information Processing and Protection (VIPP) group. His research spans digital watermarking for copyright protection, multimedia forensics, signal processing in the encrypted domain, and, more recently, adversarial machine learning and the protection of intellectual property in AI.

Prof. Benedetta Tondi

Prof. Benedetta Tondi

Assistant Professor · University of Siena

Benedetta is an Assistant Professor at the Department of Information Engineering and Mathematics, University of Siena, and a member of the VIPP Group led by Prof. Mauro Barni. Her research applies information-theoretic and game-theoretic methods to multimedia forensics, watermarking security, and adversarial signal processing for ML.

Dr. Pierre Fernandez

Dr. Pierre Fernandez

Research Scientist · Meta FAIR (Paris)

Pierre is a Research Scientist at Meta FAIR Paris. His research focuses on content protection, safety, and watermarking for generative models — making AI-generated content traceable and identifiable. He completed his PhD at FAIR / Inria Rennes with Matthijs Douze, Hervé Jégou, and Teddy Furon.

Reading List

Papers covered or referenced in the tutorial, grouped by session.

Real-World Authenticity & ProvenanceTalk 1 · 2 papers
  • Petrov, Agarwal, Torr, Bibi, Collomosse. On the coexistence and ensembling of watermarks. arXiv:2501.17356, 2025.
  • Collomosse & Parsons. To Authenticity, and Beyond! Building safe and fair generative AI upon the three pillars of provenance. IEEE CG&A, 2024.
Benchmarking & RobustnessTalk 2 · 5 papers
  • An et al. WAVES: Benchmarking the Robustness of Image Watermarks. ICML, 2024.
  • Zhao, Zhang, Su, Vasan, Grishchenko, Kruegel, Vigna, Wang, Li. Invisible Image Watermarks Are Provably Removable Using Generative AI. NeurIPS, 2024.
  • Jia, Fang, Zhang. MBRS: Enhancing robustness of DNN-based watermarking by mini-batch of real and simulated JPEG compression. ACM MM, 2021.
  • Ma, Guo, Hou, Yang, Li, Jia, Xie. Towards blind watermarking: Combining invertible and non-invertible mechanisms. ACM MM, 2022.
  • Tondi, Guo, Pancino, Barni. JMA: A General Algorithm to Craft Nearly Optimal Targeted Adversarial Examples. IEEE TIFS, 2025.
Classical FoundationsTalk 3 · 8 papers
  • Cox, Kilian, Leighton, Shamoon. Secure spread spectrum watermarking for multimedia. IEEE TIP, 1997.
  • Cox, Miller, McKellips. Watermarking as communications with side information. Proc. IEEE, 1999.
  • Chen & Wornell. Quantization index modulation: A class of provably good methods for digital watermarking and information embedding. IEEE TIT, 2001.
  • Cayre, Fontaine, Furon. Watermarking security: Theory and practice. IEEE TSP, 2005.
  • Comesaña, Pérez-Freire, Pérez-González. Fundamentals of data hiding security and their application to spread-spectrum analysis. IH, 2005.
  • Cox, Miller, Bloom, Fridrich, Kalker. Digital Watermarking and Steganography (2nd ed.). Morgan Kaufmann, 2007.
  • Fei, Xia, Tondi, Barni. Supervised GAN watermarking for intellectual property protection. WIFS, 2022.
  • Tondi, Costanzo, Barni. Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images. ICASSP, 2026.
Post-Hoc Image WatermarkingTalk 4 · 5 papers
  • Zhu, Kaplan, Johnson, Fei-Fei. HiDDeN: Hiding Data With Deep Networks. ECCV, 2018.
  • Tancik, Mildenhall, Ng. StegaStamp: Invisible Hyperlinks in Physical Photographs. CVPR, 2020.
  • Bui, Agarwal, Collomosse. TrustMark: Robust Watermarking and Watermark Removal for Arbitrary Resolution Images. ICCV, 2025.
  • Souček et al. Pixel Seal: Adversarial-only Training for Invisible Image and Video Watermarking. arXiv:2512.16874, 2025.
  • Gowal et al. SynthID-Image: Image watermarking at internet scale. arXiv:2510.09263, 2025.
Applications, Generative & Multimodal WatermarkingTalk 5 · 16 papers
  • Asnani, Yin, Liu. Proactive Schemes: A Survey of Adversarial Attacks for Social Good. IJCV, 2026.
  • Asnani et al. ProMark: Proactive Diffusion Watermarking for Causal Attribution. CVPR, 2024.
  • Kirchenbauer, Geiping, Wen, Katz, Miers, Goldstein. A Watermark for Large Language Models. ICML, 2023.
  • San Roman, Fernandez, Furon, Défossez, Tran, Elsahar. Proactive Detection of Voice Cloning with Localized Watermarking. ICML, 2024.
  • Fernandez, Elsahar, Yalniz, Mourachko. Video Seal: Open and Efficient Video Watermarking. arXiv:2412.09492, 2024.
  • Fernandez, Couairon, Jégou, Douze, Furon. The Stable Signature: Rooting Watermarks in Latent Diffusion Models. ICCV, 2023.
  • Wen, Kirchenbauer, Geiping, Goldstein. Tree-Ring Watermarks. NeurIPS, 2023.
  • Yang, Zeng, Chen, Fang, Zhang, Yu. Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models. CVPR, 2024.
  • Jovanović, Labiad, Souček, Vechev, Fernandez. Watermarking Autoregressive Image Generation. NeurIPS, 2025.
  • Darvish Rouhani, Chen, Koushanfar. DeepSigns: An end-to-end watermarking framework for ownership protection of DNNs. ASPLOS, 2019.
  • Sablayrolles, Douze, Schmid, Jégou. Radioactive Data: Tracing Through Training. ICML, 2020.
  • Li, Zhu, Yang, Jiang, Wei, Xia. Black-box dataset ownership verification via backdoor watermarking. IEEE TIFS, 2023.
  • Huang et al. CMUA-Watermark: A cross-model universal adversarial watermark for combating deepfakes. AAAI, 2022.
  • Shan, Wenger, Zhang, Li, Zheng, Zhao. Fawkes: Protecting privacy against unauthorized deep learning models. USENIX Security, 2020.
  • Luo, Guo, Cheung, See, Wan. CopyRNeRF: Protecting the Copyright of Neural Radiance Fields. ICCV, 2023.
  • Yoo, Chang, Luo, Stava, Liu, Milanfar, Yang. Deep 3D-to-2D Watermarking. CVPR, 2022.

Resources

Hands-on material, benchmarks, and tools used in the tutorial, plus the slides from all five talks.

Talk slides

Get in touch

Questions about the tutorial, accessibility requests, or collaboration ideas — we’re happy to hear from you.

Primary contact: vasnani@adobe.com

For updates as the event approaches, watch this page or the official ACM MM 2026 programme.