← Search

Quanwei Cai

2 accepted papers

2025

ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion Attacks

ACL 2025long

As the rapid expansion of Machine Learning as a Service (MLaaS) for language models, concerns over the privacy of client inputs during inference or fine-tuning have correspondingly escalated. Recently, solutions have been proposed to safeguard client privacy by obfuscation techniques. However, the s…

2024

An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference

EMNLP 2024main

With the rapidly-growing deployment of large language model (LLM) inference services, privacy concerns have arisen regarding to the user input data. Recent studies are exploring transforming user inputs to obfuscated embedded vectors, so that the data will not be eavesdropped by service provides. Ho…