AI RESEARCH
The Coding Limits of Robust Watermarking for Generative Models
arXiv CS.AI
•
ArXi:2509.10577v3 Announce Type: replace-cross We study a basic question about cryptographic watermarking for generative models: how reliable can a watermark remain when an adversary is allowed to corrupt the encoded signal? To address this question, we Within this abstraction we prove a sharp unconditional limit on robustness to independent symbol corruption.