---
title: Fedmse: Semi-Supervised Federated Learning for IoT Detection
url: https://www.ml-quant.com/papers/ssrn/4990105/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4990105
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4990105
featured: 2024-10-23
citations: unknown
topic: ML & AI Methods
---


# Fedmse: Semi-Supervised Federated Learning for IoT Detection

Semi-Supervised Federated Learning for IoT Detection: A new federated learning approach has been proposed to enhance IoT network intrusion detection, integrating the Shrink Autoencoder and Centroid one-class classifier with a new aggregation algorithm.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4990105
- Identifier: SSRN 4990105
- Released: 2024-10-17
- First featured: Quant Letter No. 71 (2024-10-23): https://www.ml-quant.com/issues/2024-10-23/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods

## Related

- [When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions](https://www.ml-quant.com/papers/arxiv/2306.15546/): Motivations, Challenges, Future Directions: The combination of Foundation Model (FM) and Federated Learning (FL) enhances AI research by increasing data availability and improving performance and convergence speed.
- [FilFL: Client Filtering for Optimized Client Participation in Federated Learning](https://www.ml-quant.com/papers/arxiv/2302.06599/): Client filtering, a new method to enhance model generalization and client participation in federated learning, has been proposed, leading to better learning efficiency, quicker convergence, and up to 10% increased test accuracy.
- [Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromises](https://www.ml-quant.com/papers/arxiv/2405.08698/): The article introduces ByITFL, a new Federated Learning scheme that protects against malicious users and ensures data privacy, marking the first Byzantine resilient scheme with full information-theoretic privacy.
- [Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimation](https://www.ml-quant.com/papers/arxiv/2406.12815/): The research reviews Federated Learning in medical imaging, discussing its challenges, potential for privacy preservation and uncertainty estimation, and suggesting future research directions.
- [Federated Combinatorial Multi-Agent Multi-Armed Bandits](https://www.ml-quant.com/papers/arxiv/2405.05950/): The study presents a federated learning framework for online combinatorial optimization, transforming single-agent algorithms into multi-agent ones, proving efficient in a stochastic data summarization problem.
- [Flame: Simplifying Topology Extension in Federated Learning](https://www.ml-quant.com/papers/arxiv/2305.05118/): Flame is a novel system for distributed machine learning that provides flexibility in setting up federated learning applications, separates application logic from deployment specifics, and supports various topologies and mechanisms.