Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning Article Swipe

MAKE IMPACT

Sayyed Farid Ahamed , Sandip Roy , Soumya Banerjee , Marc Vucovich , Kevin Choi , Abdul Rahman , Alison W. Hu , Edward Bowen , Sachin Shetty · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2505.23791

Federated Learning (FL) is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property (IP) threats. Model extraction (ME) attacks pose a significant risk to Machine Learning as a Service (MLaaS) platforms, enabling attackers to replicate confidential models by querying black-box (without internal insight) APIs. Despite FL's privacy-preserving goals, its distributed nature makes it particularly susceptible to such attacks. This paper examines the vulnerability of FL-based victim models to two types of model extraction attacks. For various federated clients built under the NVFlare platform, we implemented ME attacks across two deep learning architectures and three image datasets. We evaluate the proposed ME attack performance using various metrics, including accuracy, fidelity, and KL divergence. The experiments show that for different FL clients, the accuracy and fidelity of the extracted model are closely related to the size of the attack query set. Additionally, we explore a transfer learning based approach where pretrained models serve as the starting point for the extraction process. The results indicate that the accuracy and fidelity of the fine-tuned pretrained extraction models are notably higher, particularly with smaller query sets, highlighting potential advantages for attackers.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2505.23791

PDF

https://arxiv.org/pdf/2505.23791

OA Status

green

OpenAlex ID

https://openalex.org/W4414855132

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4414855132

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2505.23791

Digital Object Identifier

Title

Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-05-25

Full publication date if available

Authors

Sayyed Farid Ahamed, Sandip Roy, Soumya Banerjee, Marc Vucovich, Kevin Choi, Abdul Rahman, Alison W. Hu, Edward Bowen, Sachin Shetty

List of authors in order

Landing page

https://arxiv.org/abs/2505.23791

Publisher landing page

PDF URL

https://arxiv.org/pdf/2505.23791

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2505.23791

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload