SPIN Unprocessed October 28, 2026 ai_technology research
No Tokenizer, Still a Gap: Cross-Lingual Fairness of Homoglyph and Invisible-Character Watermarking
View original on arxiv.orgOverview
arXiv:2610.36432v1 Announce Type: new Abstract: Homoglyph and invisible-character watermarks are edit-based watermarks. Instead of changing how a model generates text, they hide a signal in the text after it is written. They swap some characters for homoglyphs, which look the same, or very similar, but have different Unicode code points, or they insert characters that do not display, all without access to the model that wrote the text. Generation-time watermarks work less well for lower-resource
SpinGraph analysis pending — check back after processing.
Ask AI about this story
Opens with the SpinGraph .md URL and structured context — one click, prompt included.
More from arXiv Computation and Language
View all →- Japanese Discourse Structure Analysis Based on Segmented Discourse Representation Theory Using LLMs
- Structured Maps for Landmark-Based Route Instructions with LLMs
- Agentic Data Sampling Framework for Multilingual ASR via Linguistic-Aware Error-Driven Optimization
- ETC-Bench: A Multilingual Benchmark for Evaluation-Side Transcript Canonicalization
- Causal Localization of Evidence Effects in Transformers
- Benchmarking Task Takeover Across Agent Handoffs
Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO