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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ahamed, Sayyed Farid, Roy, Sandip, Banerjee, Soumya, Vucovich, Marc, Choi, Kevin, Rahman, Abdul, Hu, Alison, Bowen, Edward, Shetty, Sachin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915313014013952
author Ahamed, Sayyed Farid
Roy, Sandip
Banerjee, Soumya
Vucovich, Marc
Choi, Kevin
Rahman, Abdul
Hu, Alison
Bowen, Edward
Shetty, Sachin
author_facet Ahamed, Sayyed Farid
Roy, Sandip
Banerjee, Soumya
Vucovich, Marc
Choi, Kevin
Rahman, Abdul
Hu, Alison
Bowen, Edward
Shetty, Sachin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23791
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
Ahamed, Sayyed Farid
Roy, Sandip
Banerjee, Soumya
Vucovich, Marc
Choi, Kevin
Rahman, Abdul
Hu, Alison
Bowen, Edward
Shetty, Sachin
Cryptography and Security
Artificial Intelligence
Machine Learning
I.2.6; D.4.6
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.
title Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning
topic Cryptography and Security
Artificial Intelligence
Machine Learning
I.2.6; D.4.6
url https://arxiv.org/abs/2505.23791