How image watermarking works: Computerphile explains Adobe's Trustmark
Computerphile · youtube · 2026-10-22
Dr Mike Pound uses Adobe's Trustmark to explain how image watermarks embed information into pictures. The video covers steganography vs watermarking and metadata limits, why LSB schemes fail, deep-learning encoder-decoder watermark architectures, code detection and reading, robustness training with augmentations, Trustmark's 256px base for arbitrary sizes, a live Python demo with stress tests (compression, resizing, cropping, color shifts), adversarial watermark-copying attacks, and AI provenance/digital signatures.
More from Research
- Embedding arithmetic demo: cartoon − animation − comic = diagram — mayfer · 2026-10-23
- Omnii Genome: Single Generalist Model Outperforms AlphaGenome Across All Benchmarks — JosephJacks_ · 2026-10-23
- Domingos Cites New Result Claiming RL Is 'Basically Useless' vs Supervised Learning — pmddomingos · 2026-10-23
- Word Arithmetic on Embeddings: "Bathroom Minus Toilet Equals Kitchen" Beats SAE Probing — mayfer · 2026-10-23
- Wolfram Opens Rule 30 Prizes to AIs: $30,000 for Three Open Problems — cephaloform · 2026-10-23
- Stanford and Databricks use AI agents to reproduce medical findings and test analytical robustness — ChengleiSi · 2026-10-23