Homomorphic Encryption-Enabled Federated Learning for Privacy-Preserving Intrusion Detection in Resource-Constrained IoV Networks

TL;DR

The paper addresses privacy challenges in FL-based intrusion detection for resource-constrained IoV networks by introducing a homomorphic-encryption-enabled FL framework. It leverages CKKS HE with SIMD and bootstrapping to enable training on encrypted data, along with a FedAvg-style aggregation to update a global encrypted model. The approach achieves approximately 91% detection accuracy, with a gap of less than 0.8% compared to plaintext baselines, demonstrating practical viability. The framework enables privacy-preserving, distributed IDS in IoV environments, balancing computational limits with security and performance needs.

Abstract

This paper aims to propose a novel framework to address the data privacy issue for Federated Learning (FL)-based Intrusion Detection Systems (IDSs) in Internet-of-Vehicles(IoVs) with limited computational resources. In particular, in conventional FL systems, it is usually assumed that the computing nodes have sufficient computational resources to process the training tasks. However, in practical IoV systems, vehicles usually have limited computational resources to process intensive training tasks, compromising the effectiveness of deploying FL in IDSs. While offloading data from vehicles to the cloud can mitigate this issue, it introduces significant privacy concerns for vehicle users (VUs). To resolve this issue, we first propose a highly-effective framework using homomorphic encryption to secure data that requires offloading to a centralized server for processing. Furthermore, we develop an effective training algorithm tailored to handle the challenges of FL-based systems with encrypted data. This algorithm allows the centralized server to directly compute on quantum-secure encrypted ciphertexts without needing decryption. This approach not only safeguards data privacy during the offloading process from VUs to the centralized server but also enhances the efficiency of utilizing FL for IDSs in IoV systems. Our simulation results show that our proposed approach can achieve a performance that is as close to that of the solution without encryption, with a gap of less than 0.8%.

Figures (5)

• Figure 1: The proposed privacy-preserving intrusion detection framework including pre-learning and privacy-preserving learning.
• Figure 2: Encrypt process of a 3x3 matrix W.
• Figure 3: Convergence of privacy-preserving learning with VUs.
• Figure 4: Classification results of 2 VUs
• Figure 5: Classification results of 3 VUs