CVPR 2026 · Half-Day Tutorial · Hybrid
Algorithms · Multimodal Extensions · Benchmarks · Authenticity Frameworks
Invisible watermarking has re-emerged as a critical pillar of trustworthy AI and media authenticity in the era of generative models. This tutorial provides a unified end-to-end treatment of watermarking, spanning classical signal-processing theory, modern deep-learning methods, multimodal extensions (image, video, audio, 3D), robustness benchmarking, and real-world deployment within industrial provenance ecosystems.
Researchers, graduate students, and practitioners in computer vision, multimedia security, and trustworthy AI who want a coherent, technically deep introduction to watermarking and its modern applications. Familiarity with deep learning fundamentals is assumed; no prior background in watermarking is required.
Conference
CVPR 2026
Date
Thursday, June 4, 2026
Time
1:00 PM – 5:00 PM
Location
Denver, Colorado, USA
Room
Mile High 2B
Format
Hybrid
This is a hybrid tutorial. In addition to the in-person session in Denver, the tutorial will be livestreamed for virtual attendees of CVPR 2026. Remote participants can follow the talks live through the official CVPR virtual platform.
All times local to Denver. Order and timing may shift slightly closer to the conference.
Dr. Vishal Asnani · Adobe Research
Why watermarking matters now: the generative-AI authenticity problem, an outline of the afternoon, and how the sessions fit together.
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.
Dr. Pierre Fernandez · Meta FAIR
Modern deep-learning watermarking organized around three axes: post-hoc encoder–decoder methods for images, their extension to other modalities (audio, video, and 3D), and the emerging paradigm of generative watermarking — including model-level fine-tuning, noise-space manipulation, and sampler-level techniques that embed the watermark during the generation process itself.
Prof. Benedetta Tondi · University of Siena
A structured journey through classical watermarking foundations: spread spectrum, quantization-based informed watermarking, the imperceptibility / payload / robustness trade-off triangle, and the rich line of work on watermark security through sensitivity and collusion attacks. We then revisit these classical principles in the modern context of post-hoc watermarking for generative AI imagery.
Prof. Furong Huang · University of Maryland
A principled framework for evaluating watermark robustness. We discuss attack taxonomies (distortion, regeneration, adversarial), evaluation criteria (BER, AUC, fidelity), and standardized stress-test benchmarks — with hands-on insights into reproducing fair comparisons across competing schemes.
Dr. Vishal Asnani · Adobe Research
Proactive schemes as a unifying framework for embedding constructive, verifiable signals into media and ML systems. We present a taxonomy spanning data perturbation, template learning, and applications across vision models, LLMs, diffusion, privacy systems, and 3D — clarifying threat models and open challenges in robust, responsible watermarking.
All organizers
Synthesis of the afternoon, audience questions across sessions, and pointers for further reading and benchmarks.
A multi-institution team spanning industry research labs and academia.
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.
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.
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.
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.
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.
A curated set of papers covered or referenced in the tutorial, grouped by session.
Slides, code, and recordings will be posted here as they become available.
Code
Reference implementations and notebook demos for selected approaches.
Coming soonVideo
Tutorial recording will be linked here after the event.
Post-eventBenchmarks
Benchmark links, datasets, and a curated extended reading list.
Coming soonQuestions 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 CVPR 2026 program listing.