Membership Inference Attack in Random Forests
Akbarian, Fatemeh LU and Aminifar, Amir LU
(2025)
ESANN 2025
- Abstract
- Machine Learning (ML) offers many opportunities, but its reliance on personal data raises privacy concerns. One such example is the Membership Inference Attack (MIA), which aims to determine whether a specific data point was part of a model’s training dataset. In this paper, we investigate this attack on Random Forests (RFs) and propose a method to quantify their vulnerability to MIA. We also demonstrate that in collaborative setups like federated learning, a client with access to the model and partial training dataset can establish MIA against other clients’ training data. The effectiveness of our method is validated through experiments.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/4d4d6520-f958-490b-a09d-41d8d6e6aff7
- author
- Akbarian, Fatemeh
LU
and Aminifar, Amir
LU
- organization
-
- LTH Profile Area: AI and Digitalization
- Secure and Networked Systems
- ELLIIT: the Linköping-Lund initiative on IT and mobile communication
- LTH Profile Area: Engineering Health
- NEXTG2COM – a Vinnova Competence Centre in Advanced Digitalisation
- LTH Profile Area: Water
- LU Profile Area: Natural and Artificial Cognition
- publishing date
- 2025-04-23
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2025)
- pages
- 6 pages
- publisher
- European Symposium on Artificial Neural Networks
- conference name
- ESANN 2025
- conference location
- Bruges, Belgium
- conference dates
- 2025-04-23 - 2025-04-25
- ISBN
- 9782875870933
- language
- English
- LU publication?
- yes
- id
- 4d4d6520-f958-490b-a09d-41d8d6e6aff7
- alternative location
- https://www.esann.org/sites/default/files/proceedings/2025/ES2025-184.pdf
- date added to LUP
- 2025-11-24 16:15:18
- date last changed
- 2025-11-26 09:35:51
@inproceedings{4d4d6520-f958-490b-a09d-41d8d6e6aff7,
abstract = {{Machine Learning (ML) offers many opportunities, but its reliance on personal data raises privacy concerns. One such example is the Membership Inference Attack (MIA), which aims to determine whether a specific data point was part of a model’s training dataset. In this paper, we investigate this attack on Random Forests (RFs) and propose a method to quantify their vulnerability to MIA. We also demonstrate that in collaborative setups like federated learning, a client with access to the model and partial training dataset can establish MIA against other clients’ training data. The effectiveness of our method is validated through experiments.}},
author = {{Akbarian, Fatemeh and Aminifar, Amir}},
booktitle = {{European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2025)}},
isbn = {{9782875870933}},
language = {{eng}},
month = {{04}},
publisher = {{European Symposium on Artificial Neural Networks}},
title = {{Membership Inference Attack in Random Forests}},
url = {{https://lup.lub.lu.se/search/files/233843337/Membership_Inference_Attack_in_Random_Forests.pdf}},
year = {{2025}},
}