Active Membership Inference Attack under Local Differential Privacy in Federated Learning

Truc Nguyen, Phung Lai, Khang Tran, NhatHai Phan, My T. Thai
2/24/2023
cs.LGcs.AIcs.CR

No official code found. Best implementation: trucndt/ami (16 stars, last commit 2024-02-09).

Abstract

Federated learning (FL) was originally regarded as a framework for collaborative learning among clients with data privacy protection through a coordinating server. In this paper, we propose a new active membership inference (AMI) attack carried out by a dishonest server in FL. In AMI attacks, the server crafts and embeds malicious parameters into global models to effectively infer whether a target data sample is included in a client's private training data or not. By exploiting the correlation among data features through a non-linear decision boundary, AMI attacks with a certified guarantee of success can achieve severely high success rates under rigorous local differential privacy (LDP) protection; thereby exposing clients' training data to significant privacy risk. Theoretical and experimental results on several benchmark datasets show that adding sufficient privacy-preserving noise to prevent our attack would significantly damage FL's model utility.

View on arXivView PDF

Code Implementations(1)

trucndt/amiCommunity100%

Codebase for Active Membership Inference Attack under Local Differential Privacy in Federated Learning

162PythonFeb 23, 20232 years ago
machine-learningmembership-inference-attack

Similar Papers

Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach

90% match2024

Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation

90% match2023

MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learning

90% match1 repo2023

Accuracy-Privacy Trade-off in the Mitigation of Membership Inference Attack in Federated Learning

90% match2024

FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning

90% match1 repo202024

Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning

90% match2026

Cite this paper

@article{nguyen2023active,
  title  = {Active Membership Inference Attack under Local Differential Privacy in Federated Learning},
  author = {Truc Nguyen and Phung Lai and Khang Tran and NhatHai Phan and My T. Thai},
  year   = {2023},
  eprint = {2302.12685},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.12685v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.12685.svg)](https://codeofpaper.com/paper/2302.12685)

Discussion