Tokenization-Invariant Watermarking: A Byte-Local Method for LLM Text
cs.CR, cs.CL
Submitted: 2026-10-09
Updated: 2026-10-09
Terminology
Sources
- PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Semantic-Invariant Attacks
- Three Bricks to Consolidate Watermarks for Large Language Models
- Robust Distortion-free Watermarks for Language Models
- MarkSec: Capability-Aware Evaluation of Adversarial Attacks Against LLM Watermarks
- LLM Watermarking as Big Data Provenance: A Deployment-Oriented Systematization
- Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models
- Character-Level Perturbations Disrupt LLM Watermarks
- Provable Robust Watermarking for AI-Generated Text
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