paper-with-me

홈 › Papers

k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text

2024-02-17 · Abe Bohan Hou, Jingyu Zhang, Yichen Wang, Daniel Khashabi, Tianxing He

Recent watermarked generation algorithms inject detectable signatures during language generation to facilitate post-hoc detection. While token-level watermarks are vulnerable to paraphrase attacks, SemStamp (Hou et al., 2023) applies watermark on the semantic representation of sentences and demonstrates promising robustness. SemStamp employs locality-sensitive hashing (LSH) to partition the semantic space with arbitrary hyperplanes, which results in a suboptimal tradeoff between robustness and speed. We propose k-SemStamp, a simple yet effective enhancement of SemStamp, utilizing k-means clustering as an alternative of LSH to partition the embedding space with awareness of inherent semantic structure. Experimental results indicate that k-SemStamp saliently improves its robustness and sampling efficiency while preserving the generation quality, advancing a more effective tool for machine-generated text detection.

📄 PDF Abstract BibTeX arXiv:2402.11399

Code (2)

bohanhou14/semstamp 공식 구현 pytorch
DabiriAghdam/SimMark pytorch

Tasks

Text DetectionText Generation

Methods 이 논문이 사용한 방법론

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

Similar Papers 제목 키워드 기반

SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation

2023-10-06 · Abe Bohan Hou, Jingyu Zhang, Tianxing He, Yichen Wang 외

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 loca…

SentenceText Generation

CATMark: A Context-Aware Thresholding Framework for Robust Cross-Task Watermarking in Large Language Models

2025-09-27 · Yu Zhang, Shuliang Liu, Xu Yang, Xuming Hu arxiv

Watermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, such embedding leads to a decline in text q…

Text Generation

Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy

2023-07-25 · Yu Fu, Deyi Xiong, Yue Dong

To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this informatio…

Conditional Text GenerationData-to-Text GenerationText Generation

Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation

2025-10-20 · Asim Mohamed, Martin Gubri arxiv

Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages, yet current methods still fall short. Despite claims of cross-lingual robustness, they are evaluated only on high-reso…

ClusterMark: Towards Robust Watermarking for Autoregressive Image Generators with Visual Token Clustering

2025-08-08 · Denis Lukovnikov, Andreas Müller, Erwin Quiring, Asja Fischer arxiv

In-generation watermarking for latent diffusion models has recently shown high robustness in marking generated images for easier detection and attribution. However, its application to autoregressive (AR) image models is …