arXiv (All)
open access
Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key
Multi-bit watermarking embeds a message, typically an account identifier, into LLM output so that harmful text can be traced to its origin. We show an attack technique that allows to alter the watermarking message. This allows to, for example, exchange the embedded account ID to an arbitrary differe
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key#1318883
- A Survey on LLM Watermarking: Theory and Deployment#363199
- Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes#1143323
- Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes#1136793
- Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection#222554
Record · ID 1343870
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive