paper-with-me

Papers

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks

2024-08-29 · Anudeex Shetty, Qiongkai Xu, Jey Han Lau

Embeddings-as-a-Service (EaaS) is a service offered by large language model (LLM) developers to supply embeddings generated by LLMs. Previous research suggests that EaaS is prone to imitation attacks -- attacks that clone the underlying EaaS model by training another model on the queried embeddings. As a result, EaaS watermarks are introduced to protect the intellectual property of EaaS providers. In this paper, we first show that existing EaaS watermarks can be removed by paraphrasing when attackers clone the model. Subsequently, we propose a novel watermarking technique that involves linearly transforming the embeddings, and show that it is empirically and theoretically robust against paraphrasing.

📄 PDF Abstract BibTeX arXiv:2409.04459

Code (1)

anudeex/wet 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

Watermarks for Embeddings-as-a-Service Large Language Models

2025-11-28 · Anudeex Shetty arxiv

Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. Based on these LLMs, businesses have started to provide Embeddings-as-a-Service (EaaS), offering f…

Natural Language Understanding

Analogies Explained: Towards Understanding Word Embeddings

2019-01-28 · Carl Allen, Timothy Hospedales

Word embeddings generated by neural network methods such as word2vec (W2V) are well known to exhibit seemingly linear behaviour, e.g. the embeddings of analogy "woman is to queen as man is to king" approximately describe…

Word Embeddings

Paraphrasing Out-of-Vocabulary Words with Word Embeddings and Semantic Lexicons for Low Resource Statistical Machine Translation

2016-05-01 · LREC 2016 5 · Chenhui Chu, Sadao Kurohashi

Out-of-vocabulary (OOV) word is a crucial problem in statistical machine translation (SMT) with low resources. OOV paraphrasing that augments the translation model for the OOV words by using the translation knowledge of …

Machine TranslationTranslationWord Embeddings

Comparative Study of Sentence Embeddings for Contextual Paraphrasing

2020-05-01 · LREC 2020 5 · Louisa Pragst, Wolfgang Minker, Stefan Ultes

Paraphrasing is an important aspect of natural-language generation that can produce more variety in the way specific content is presented. Traditionally, paraphrasing has been focused on finding different words that conv…

ClusteringSentenceSentence EmbeddingsText Generation

RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection

2025-11-17 · Shufan Yang, Zifeng Cheng, Zhiwei Jiang, Yafeng Yin 외 arxiv

Embedding-as-a-Service (EaaS) is an effective and convenient deployment solution for addressing various NLP tasks. Nevertheless, recent research has shown that EaaS is vulnerable to model extraction attacks, which could …

Dimensionality ReductionModel extraction