# Leveraging Membership Inference Attacks for Privacy Measurement in Federated Learning for Remote Sensing Images

arXiv: https://arxiv.org/abs/2601.06200 · HTML: https://mlsanity.com/paper/2601.06200/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 10 of 10)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification](https://mlsanity.com/paper/1608.05167/) (2016)
- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [Membership Inference Attacks and Defenses in Federated Learning: A Survey](https://mlsanity.com/paper/2412.06157/) (2024)
- [Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction](https://mlsanity.com/paper/2307.01610/) (2023)
- [Federated Learning Across Decentralized and Unshared Archives for Remote Sensing Image Classification](https://mlsanity.com/paper/2311.06141/) (2023)
- [GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation](https://mlsanity.com/paper/2405.07562/) (2024)
- [Leveraging feature communication in federated learning for remote sensing image classification](https://mlsanity.com/paper/2403.13575/) (2024)

## Abstract (arXiv)

Federated Learning (FL) enables collaborative model training while keeping training data localized, allowing us to preserve privacy in various domains including remote sensing. However, recent studies show that FL models may still leak sensitive information through their outputs, motivating the need for rigorous privacy evaluation. In this paper, we leverage membership inference attacks (MIA) as a quantitative privacy measurement framework for FL applied to remote sensing image classification. We evaluate multiple black-box MIA techniques, including entropy-based attacks, modified entropy attacks, and the likelihood ratio attack, across different FL algorithms and communication strategies. Experiments conducted on two public scene classification datasets demonstrate that MIA effectively reveals privacy leakage not captured by accuracy alone. Our results show that communication-efficient FL strategies reduce MIA success rates while maintaining competitive performance. These findings confirm MIA as a practical metric and highlight the importance of integrating privacy measurement into FL system design for remote sensing applications.