码本搜索实现多比特 LLM 水印：短文本溯源新方法

View PDF HTML (experimental)

Abstract:Attributing short LLM-generated texts to a specific source remains challenging for existing multi-bit watermarking methods, which often require long generations or costly decoding to recover payloads reliably. We propose a codebook-based watermarking scheme that maps an $n$-bit payload to a longer $u$-bit codeword and embeds it during generation through token-level logit biasing. During extraction, the received bit sequence is matched to the nearest codeword in a precomputed secret codebook using Hamming or Levenshtein distance. Experiments show that our method achieves near-perfect recovery for 16-24 bit payloads on 200-token generations and strong performance on 127-token generations for base models. Results are weaker on some instruction-tuned models with very short texts, where low-entropy output distributions reduce embedding reliability. We also study a BCH-based variant that avoids codebook storage but generally reduces robustness. The Levenshtein variant improves resilience to deletions and light paraphrasing, while insertions and stronger rewrites remain challenging. We analyze collision probability, codeword separation, extraction time, tokenization consistency, and text quality, highlighting both the practicality and limitations of codebook-based watermarking for short-form attribution.

Comments:	16 pages, 8 figures, 6 tables. Submitted to IEEE Transactions on Information Forensics and Security. Code: this https URL
Subjects:	Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as:	arXiv:2611.16890 [cs.CR]
	(or arXiv:2611.16890v1 [cs.CR] for this version)
	https://doi.org/10.48550/arXiv.2611.16890 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jarosław Janas [view email]
[v1] Thu, 12 Nov 2026 14:49:23 UTC (1,546 KB)