Searcharxiv⌕ Search

arXiv · 2611.19305

Fundamental Limits of Statistical Watermarking for LLMs with Fixed and Optimizable Common Randomness

Abstract

Watermarking has emerged as an important technique for distinguishing AI-generated text from human-written text. However, most existing work is primarily empirical, relies on ad hoc watermarking designs, and lacks a fundamental understanding of the performance limits. In this paper, we propose a unified theoretical framework for statistical watermarking of large language models (LLMs), casting the problem as an independence test between generated text and common randomness and jointly designing the watermarking embedder and the detector. Our objective is to maximize detection power while controlling the worst-case false positive rate (FPR) and limiting distortion to text quality. A central focus of our framework is the design of the common randomness, which plays a critical role in both watermark embedding and detection. We characterize the fundamental limits of statistical watermarking under both fixed and optimizable common randomness. Our results show that optimizing the common randomness does not improve the fundamental limits: the best achievable performance is the same as that with fixed common randomness. Nevertheless, common randomness design remains highly important because it can substantially simplify detector design. In particular, with optimizable common randomness, a fixed, deterministic, and model-agnostic detector can achieve optimal performance. We further study a practical setting with fixed uniform common randomness and a fixed deterministic detector, and characterize its performance gap relative to the optimizable case, thereby demonstrating the practical value of optimizable common randomness.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Haiyun He, Yepeng Liu, Zhuoer Shen, Ziqiao Wang, Yongyi Mao, Yuheng Bu. 2026-11-14. Fundamental Limits of Statistical Watermarking for LLMs with Fixed and Optimizable Common Randomness. https://searcharxiv.com/abs/2611.19305

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related papers

Frames over finite fields with respect to the Galois inner product and their connections to self-orthogonal and LCD codes

In this paper, we generalize the theory of frames to vector spaces over finite fields equipped with the $\ell$-Galois inner product. We introduce $\ell$-Galois analogues of fundamental concepts in frame theory and investigate extensions of existing results to the $\ell$-Galois setting. In particular, we establish necessary and sufficient conditions for a given matrix to be the $\ell$-Galois Gram matrix of a frame and show that such frames are unique up to isometry. We also extend Gerzon's bound to $\ell$-Galois equiangular systems and show that equality in this bound yields an $\ell$-Galois equiangular tight frame. Furthermore, we investigate the connections between $\ell$-Galois frames and $\ell$-Galois self-orthogonal and LCD codes over finite fields. We establish necessary and sufficient conditions for constructing $\ell$-Galois equiangular tight frames from self-dual codes, generalizing existing results by Shi et al. on the relationship between frames and self-dual codes over finite fields. Beyond self-dual codes, we provide sufficient conditions for constructing $\ell$-Galois equiangular tight frames from linear codes using their automorphism groups, together with explicit examples.

cs.IT↗

Efficient and rate-optimal list-decoding in the presence of minimal feedback

Given a channel with length-$n$ inputs and outputs over the alphabet $\{0,1,\ldots,q-1\}$, and of which a fraction $\varrho \in (0,1-1/q)$ of symbols can be arbitrarily corrupted by an adversary, a fundamental problem is that of communicating at rates close to the information-theoretically optimal values, while ensuring the receiver can infer that the transmitter's message is from a ``small" set. While the existence of such codes is known, and constructions with computationally tractable encoding/decoding procedures are known for large $q$, we provide the first schemes that attain this performance for any $q \geq 2$, as long as low-rate feedback (asymptotically negligible relative to the number of transmissions) from the receiver to the transmitter is available. For any sufficiently small $\varepsilon > 0$ and $\varrho \in (1-{1}/{q}-Θ(\sqrt{\varepsilon}))$ our minimal feedback scheme has the following parameters: Rate $1-H_q(\varrho) - \varepsilon$ (i.e., $\varepsilon$-close to information-theoretically optimal -- here $H_q(\varrho)$ is the $q$-ary entropy function), list-size $\exp\left(\mathcal{O}\left(\varepsilon^{-3/2}\log^2(1/\varepsilon)\right)\right)$, computational complexity of encoding/decoding $n^{\mathcal{O}(\varepsilon^{-1}\log(1/\varepsilon))}$, storage complexity $\mathcal{O}(n^{η+1}\log n)$ for a code design parameter $η>1$ that trades off storage complexity with the probability of error. The error probability is $\mathcal{O}(n^{-η})$, and the (vanishing) feedback rate is $\mathcal{O}({1}/{\sqrt{\log(n)}})$. Our full-feedback scheme has zero probability of error and minimal storage complexity, while the other parameters are the same as the vanishing rate feedback scheme.

cs.IT↗

On concatenation of matrices for reversible linear codes over a finite commutative ring and applications to DNA codes

In this paper, we develop a generalized framework for constructing reversible linear, reversible self dual and reversible DNA codes using a matrix-theoretic approach based on involutory matrices. The proposed concatenation scheme gives a large class of generator matrices and yields codes with good parameters. The construction is carried out at the level of linear codes and then extended to DNA codes. Using a matrix product approach, we provide a unified method for analysis and proof. Further, we resolve an open problem raised by Oztas et.al. and also we correct and improve some results of them.

cs.IT↗