Federated Learning Approaches for Privacy-Preserving Malware Detection

EasyChair Preprint 14120

Abstract

The rapid growth of malware poses a significant threat to the security and privacy of individuals and organizations. Traditional malware detection approaches rely on centralized models, where sensitive data is shared with a central server for analysis. However, this approach raises concerns about privacy and data security.

In recent years, federated learning has emerged as a promising solution for privacy-preserving malware detection. This approach allows multiple entities to collaboratively train a shared model without sharing their raw data. By keeping the data decentralized, federated learning mitigates the risk of data breaches and protects the privacy of individuals.

This paper reviews the current state of federated learning approaches for privacy-preserving malware detection and highlights their advantages and limitations. We discuss various techniques used in federated learning, such as secure aggregation, differential privacy, and homomorphic encryption, to ensure the privacy and security of the data.

Keyphrases: Federated Learning, Traditional malware detection, privacy preserving

@booklet{EasyChair:14120,
  author    = {Brown Klinton and Peter Broklyn and Sabir Kashar},
  title     = {Federated Learning Approaches for Privacy-Preserving Malware Detection},
  howpublished = {EasyChair Preprint 14120},
  year      = {EasyChair, 2024}}