相关论文: Permute-and-Flip: An optimally stable and watermar…

We study how to watermark LLM outputs, i.e. embedding algorithmically detectable signals into LLM-generated text to track misuse. Unlike the current mainstream methods that work with a fixed LLM, we expand the watermark design space by…

The permute-and-flip mechanism is a recently proposed differentially private selection algorithm that was shown to outperform the exponential mechanism. In this paper, we show that permute-and-flip is equivalent to the well-known report…

A new local watermarking method based on histogram shifting has been proposed in this paper to deal with various signal processing attacks (e.g. median filtering, JPEG compression and Gaussian noise addition) and geometric attacks (e.g.…

The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs' outputs traceable without requiring…

LLM watermarks stand out as a promising way to attribute ownership of LLM-generated text. One threat to watermark credibility comes from spoofing attacks, where an unauthorized third party forges the watermark, enabling it to falsely…

Invisible watermarking is essential for safeguarding digital content, enabling copyright protection and content authentication. However, existing watermarking methods fall short in robustness against regeneration attacks. In this paper, we…

Existing watermarking methods for large language models (LLMs) mainly embed watermark by adjusting the token sampling prediction or post-processing, lacking intrinsic coupling with LLMs, which may significantly reduce the semantic quality…

Vulnerability of watermarking schemes against intense signal processing attacks is generally a major concern, particularly when there are techniques to reproduce an acceptable copy of the original signal with no chance for detecting the…

Reed-Muller (RM) and polar codes are a class of capacity-achieving channel coding schemes with the same factor graph representation. Low-complexity decoding algorithms fall short in providing a good error-correction performance for RM and…

We propose a methodology for planting watermarks in text from an autoregressive language model that are robust to perturbations without changing the distribution over text up to a certain maximum generation budget. We generate watermarked…

The rise of LLMs has increased concerns over source tracing and copyright protection for AIGC, highlighting the need for advanced detection technologies. Passive detection methods usually face high false positives, while active watermarking…

The increasing use of Large Language Models (LLMs) for generating highly coherent and contextually relevant text introduces new risks, including misuse for unethical purposes such as disinformation or academic dishonesty. To address these…

Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike autoregressive…

Federated learning (FL) enables fine-tuning large language models (LLMs) across distributed data sources. As these sources increasingly include LLM-generated text, provenance tracking becomes essential for accountability and transparency.…

Large language models (LLMs) have shown impressive capabilities in adapting to various tasks when provided with task-specific instructions. However, LLMs using standard decoding strategies often struggle with deviations from the inputs.…

We design Snowflake, a quantum error correction decoder that, for the surface code under circuit-level noise, is roughly 25% more accurate than the Union-Find decoder, with a better mean runtime scaling: subquadratic as opposed to cubic in…

Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and…

Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. However, existing watermarking methods are often vulnerable to semantic-invariant attacks, such as…

Homomorphic permutation is fundamental to privacy-preserving computations based on batch-encoding homomorphic encryption. It underpins nearly all homomorphic matrix operations and predominantly influences their complexity. Permutation…

A novel recursive list decoding (RLD) algorithm for Reed-Muller (RM) codes based on successive permutations (SP) of the codeword is presented. A low-complexity SP scheme applied to a subset of the symmetry group of RM codes is first…