SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation
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.
Code (2)
Tasks
SentenceText GenerationSimilar Papers 제목 키워드 기반
k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
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., …
Text DetectionText GenerationA Semantic Invariant Robust Watermark for Large Language Models
Watermark algorithms for large language models (LLMs) have achieved extremely high accuracy in detecting text generated by LLMs. Such algorithms typically involve adding extra watermark logits to the LLM's logits at each…
Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings
This work presents Dual-Embedding Watermarking (DEW), a semantic watermarking scheme for large language models (LLMs) that leverages contextual and token-level embeddings to enhance robustness against paraphrasing and tr…
Robustness Assessment and Enhancement of Text Watermarking for Google's SynthID
Recent advances in LLM watermarking methods such as SynthID-Text by Google DeepMind offer promising solutions for tracing the provenance of AI-generated text. However, our robustness assessment reveals that SynthID-Text …
Information RetrievalSimKey: A Semantically Aware Key Module for Watermarking Language Models
The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can em…