Watermark Forensics for Generative Models: An Information-Theoretic Perspective
A watermark in a generative model's output is usually asked only whether a text is machine-made. The same mark can do more: attribute it to the user who produced it, extract a hidden payload, or localize the part that survives editing. These form a forensic ladder, and we ask what each rung costs in the sample length $n$. One object organizes the answers. Let $S$ be the secret the mark carries (a user's identity or payload), and let the information profile $ν(t)=I(S;X_t\mid X_{
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Xiaoyu Li →
“Watermark Forensics for Generative Models: An Information-Theoretic Perspective”
- LinkedLinked via arxiv author · 85%Zheng Gao →
“Watermark Forensics for Generative Models: An Information-Theoretic Perspective”
- LinkedLinked via arxiv author · 85%Xiaoyan Feng →
“Watermark Forensics for Generative Models: An Information-Theoretic Perspective”
- LinkedLinked via arxiv author · 85%Jiaojiao Jiang →
“Watermark Forensics for Generative Models: An Information-Theoretic Perspective”
- LinkedLinked via arxiv author · 85%Yulei Sui →
“Watermark Forensics for Generative Models: An Information-Theoretic Perspective”
- LinkedLinked via arxiv author · 85%Jiankun Hu →
“Watermark Forensics for Generative Models: An Information-Theoretic Perspective”
- FuzzySimilar title/name (fuzzy) · 84%GoogleCloudPlatform/generative-ai →
“Fuzzy title match (0.92): “Watermark Forensics for Generative Models: An Information-Th” ≈ “GoogleCloudPlatform/generative-ai””
- FuzzyOverlapping authors or contributors · 62%affaan-m/ECC →
“Shared author/contributor keys: jiang”