Federated Learning for Privacy-Preserving Intrusion Detection: A Systematic Review, Taxonomy, Challenges and Future Directions
Abstract
This paper presents a systematic review of intrusion detection systems (IDS) that leverage federated learning (FL) to enhance privacy in distributed cybersecurity environments.A total of 78 peer-reviewed studies published between 2019 and 2024 were selected using PRISMA guidelines.We categorize FL-based IDS solutions based on architecture (centralized, decentralized, hierarchical), aggregation methods (e.g., FedAvg, DAFL), and privacy-preserving techniques (e.g., differential privacy, homomorphic encryption).The survey also examines solutions to key challenges such as communication overhead, data heterogeneity, and poisoning attacks.Furthermore, this study outlines unresolved issues and proposes future research directions, including adaptive federated optimization and cross-domain deployments.This review serves as a valuable resource for researchers and practitioners aiming to develop privacy-aware, scalable, and intelligent IDS using federated learning.
How strong is the evidence?
Evidence Hub reads this as a systematic review. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.