SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation
read the original abstract
Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. To address this issue, we propose SemStamp, a robust sentence-level semantic watermarking algorithm based on locality-sensitive hashing (LSH), which partitions the semantic space of sentences. The algorithm encodes and LSH-hashes a candidate sentence generated by an LLM, and conducts sentence-level rejection sampling until the sampled sentence falls in watermarked partitions in the semantic embedding space. A margin-based constraint is used to enhance its robustness. To show the advantages of our algorithm, we propose a "bigram" paraphrase attack using the paraphrase that has the fewest bigram overlaps with the original sentence. This attack is shown to be effective against the existing token-level watermarking method. Experimental results show that our novel semantic watermark algorithm is not only more robust than the previous state-of-the-art method on both common and bigram paraphrase attacks, but also is better at preserving the quality of generation.
This paper has not been read by Pith yet.
Forward citations
Cited by 13 Pith papers
-
SLAM: Structural Linguistic Activation Marking for Language Models
SLAM achieves 100% detection on Gemma-2 models with only 1-2 point quality cost by causally steering SAE-identified residual-stream directions for linguistic structure.
-
SLAM: Structural Linguistic Activation Marking for Language Models
SLAM achieves 100% detection accuracy on Gemma-2 models with only 1-2 points of quality loss by causally steering SAE-identified structural directions while preserving lexical sampling and semantics.
-
SWAN: Semantic Watermarking with Abstract Meaning Representation
SWAN uses AMR to embed semantic watermarks that persist through paraphrases, matching SOTA detection on original text and improving AUC by 13.9 points on paraphrased RealNews data.
-
Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends
A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.
-
LLM Self-Recognition: Steering and Retrieving Activation Signatures
Steering LLM residual streams with random sparse vectors creates detectable self-recognition fingerprints that enable over 98% accurate attribution of generated text to specific models without degrading output quality.
-
Global Sketch-Based Watermarking for Diffusion Language Models
Introduces a sketch-based watermarking method for masked diffusion language models providing an order-agnostic detection statistic decoupled from local context.
-
Show, Don't TELL: Explainable AI-Generated Text Detection
TELL is a new architecture for AI text detection that natively supplies explanatory annotations, reaching AUROC 0.927 and a 72.3% human win-rate on explanation quality metrics.
-
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
SAMark uses self-anchored semantic green regions, multi-channel hyperbolic scoring, and diversity-aware filtering to reach 90.2% TP@FP1% detection under paragraph paraphrasing while preserving text quality.
-
Watermarking Should Be Treated as a Monitoring Primitive
Watermarking enables entity-level attribution and monitoring via signal aggregation across outputs, even in zero-bit designs, revealing a fundamental tension with attribution goals.
-
Watermarking Should Be Treated as a Monitoring Primitive
Watermarking enables entity-level attribution and monitoring through signal aggregation even in zero-bit designs, creating an unavoidable dual-use tension between attribution and surveillance.
-
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
TextSeal provides a localized, distortion-free LLM watermark that enables provenance tracking and distillation detection while preserving performance and text quality.
-
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
TextSeal provides a localized, distortion-free LLM watermark that outperforms baselines in detection strength, remains effective in mixed human-AI text, preserves model performance, and transfers through distillation ...
-
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.