Secure Intrusion Detection based on Homomorphic Encryption and Secret Sharing

DOI

10.2991/978-94-6463-845-5_98How to use a DOI?

Keywords

Intrusion Detection System; FHE; BFV; Secret Sharing; Privacy Protection; Network; Data

Abstract

With the increasing complexity of network attack methods, there are serious data leakage risks and system stability problems in traditional Intrusion Detection System (IDS) in data collection, transmission, a1nalysis and storage. Therefore, this paper proposes a Private Secure Intrusion Detection System (PSIDS) that integrates Fully Homomorphic Encryption (FHE) and Shamir secret sharing mechanism. Build an end-to-end data protection and anti-attack system. PSIDS introduces an encryption and decryption layer on the basis of the traditional three-layer architecture, and uses the BFV algorithm to encrypt the original traffic, so that the detection node can directly perform detection and analysis on the encrypted data, achieving “data available but not visible”; At the same time, the Shamir (t, n) threshold secret sharing mechanism is introduced in the system, and the key data of the intrusion detection model are divided into n shares for distributed storage. Only when at least t nodes cooperate, the original information can be reconstructed, which effectively resists single-point attacks and improves the robustness of the system. The experiment compares PSIDS with Centralized IDS, Distributed IDS and Machine Learning based IDS. The results show that PSIDS has achieved breakthroughs in data privacy and system stability. The collaborative application of FHE and secret sharing technology in IDS is realized for the first time.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Peiyin Yao
PY  - 2025
DA  - 2025/09/16
TI  - Secure Intrusion Detection based on Homomorphic Encryption and Secret Sharing
BT  - Proceedings of the 2025 6th International Conference on Management Science and Engineering Management (ICMSEM 2025)
PB  - Atlantis Press
SP  - 1010
EP  - 1018
SN  - 2667-1271
UR  - https://doi.org/10.2991/978-94-6463-845-5_98
DO  - 10.2991/978-94-6463-845-5_98
ID  - Yao2025
ER  -