Score: 2

Imitative Membership Inference Attack

Published: September 8, 2025 | arXiv ID: 2509.06796v1

By: Yuntao Du , Yuetian Chen , Hanshen Xiao and more

Potential Business Impact:

Finds if private data was used to train AI.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

A Membership Inference Attack (MIA) assesses how much a target machine learning model reveals about its training data by determining whether specific query instances were part of the training set. State-of-the-art MIAs rely on training hundreds of shadow models that are independent of the target model, leading to significant computational overhead. In this paper, we introduce Imitative Membership Inference Attack (IMIA), which employs a novel imitative training technique to strategically construct a small number of target-informed imitative models that closely replicate the target model's behavior for inference. Extensive experimental results demonstrate that IMIA substantially outperforms existing MIAs in various attack settings while only requiring less than 5% of the computational cost of state-of-the-art approaches.

Repos / Data Links

Page Count
24 pages

Category
Computer Science:
Cryptography and Security