Optimizing and Securing the Modern Watermarking Channel for Images

arXiv:2609.34744 · cs.CR, cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CR, cs.CV

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Robustness — 20× in this paper · explained in 5 episodes
• Adversarial Robustness — 12× in this paper · explained in 3 episodes
• Steering — 8× in this paper · explained in 2 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Alignment — 6× in this paper · explained in 1 episode
• Latent Space — 5× in this paper · explained in 7 episodes
• Redundancy — 5× in this paper · explained in 2 episodes
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• Loss Function — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Secure Neural Watermarking — 2× in this paper
• Adversarial Training — 1× in this paper · explained in 1 episode
• Binary Phase-Shift Keying — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Discrete Wavelet Transform — 1× in this paper
• Distance Preservation — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• International Workshop on Information Forensics and Security — 1× in this paper
• Latent Representation — 1× in this paper · explained in 2 episodes
• Principal Component Analysis — 1× in this paper
• Principal Component Analysis (PCA) — 1× in this paper · explained in 4 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Wavelet Transform — 1× in this paper · explained in 2 episodes

Sources

• Video Seal: Open and Efficient Video Watermarking
• Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles
• SynthID-Image: Image watermarking at internet scale
• UnMarker: A Universal Attack on Defensive Image Watermarking
• We Can Hide More Bits: The Unused Watermarking Capacity in Theory and in Practice
• Learning to Watermark in the Latent Space of Generative Models
• Pixel Seal: Adversarial-only training for invisible image and video watermarking
• Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
• Improved subspace estimation for multivariate observations of high dimension: the deterministic signals case

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs