arXiv AI
Watermarking Should Be Treated as a Monitoring Primitive
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 9
Could LLM Watermark Detection be Public?
The paper investigates whether releasing a public detector for large language model (LLM) watermarks is safe. It first assesses the risk of a public detector at different access levels, then proposes a split-key watermarking scheme that publishes one key for public detection while keeping a second key private for full verification. Experiments show that public detection only slightly improves watermark removal under limited edit budgets but enables forgery, which the private pipeline can detect, suggesting that releasing half of the watermark can provide transparency without significantly increasing liability.
arXiv AI
Oct 5
Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
The paper proposes a defense against watermark forgery in generative models by randomizing the selection of watermark keys for each query and accepting content only if exactly one key detects a watermark. This approach provides a sample‑count‑independent upper bound on forgery success for blind attackers while preserving model utility. Experiments show a dramatic drop in forgery success rates—from 87% to 1% with four keys for text and from 100% to 2% for images—without significant computational overhead.
arXiv Computer Vision
Sep 1
Asymmetric Phase Coding Video Watermarking
arXiv:2608.29212v1 Announce Type: cross Abstract: Existing video watermarking systems are symmetric: the party that can verify a mark holds the extractor weights or generator secret and can therefore...
arXiv Computer Vision
Oct 1
Persistent Watermarking of Text-to-Image Models
arXiv:2609.39024v1 Announce Type: new Abstract: Text-to-image (T2I) generation is gaining increasing popularity with the general public, motivating the development of reliable mechanisms for copyrigh...
arXiv AI
Aug 5
Attribute-based Undetectable Watermarking for Generative AI Models
arXiv:2608. 03174v1 Announce Type: cross Abstract: Generative AI systems increasingly produce content whose provenance is difficult to verify, motivating watermarking techniques for identifying model-generated outputs.
arXiv AI
Oct 1
WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against Attacks
arXiv:2609.40031v1 Announce Type: cross Abstract: Digital image watermarking is increasingly critical in media contexts, as emerging regulations and industry practices require marking AI-generated co...