Foundations and Frontiers of Watermarking

Algorithms · Multimodal Extensions · Benchmarks · Authenticity Frameworks

CVPR 2026 Tutorial · Half-Day · In Person

Overview

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 (WAVES), and real-world deployment within provenance ecosystems such as C2PA and Content Credentials.

Speakers

Dr. Vishal Asnani

Adobe Research

Dr. Shruti Agarwal

Adobe Research

Prof. Benedetta Tondi

University of Siena

Dr. Pierre Fernandez

Meta AI (FAIR)

Prof. Furong Huang

University of Maryland

Schedule

08:30 – 08:35 Introduction & Motivation

08:35 – 09:20 Watermarking Before and After Deep Learning

09:20 – 10:05 Multimodal Watermarking

10:15 – 11:00 Benchmarking with WAVES

11:00 – 11:45 GenAI Watermarking & Attribution

11:55 – 12:40 C2PA & Real-World Deployment

12:40 – 12:45 Closing Remarks

Resources

Slides: Coming Soon
GitHub Repository: (Link will be added)
Reading List & Benchmarks: Coming Soon

Selected References

Cox et al., Digital Watermarking, 2001
Tancik et al., StegaStamp, CVPR 2020
Fernandez et al., Stable Signature, ICCV 2023
An et al., WAVES, ICML 2024
Asnani et al., ProMark, CVPR 2024