We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.04459")
get_code_for_paper("2409.04459")
have("2409.04459")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2409.04459.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2409.04459)
Connect an agent — have() is free.