Privacy-preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model
Knowledge transfer is critical in making use of data from multi-source domains, but most existing techniques are not privacy-preserving. Nowadays, data leakage, together with the advancement of big-data-driven Artificial Intelligence, has raised huge concerns over data security. The neglect of priva...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/163890 |
| _version_ | 1824456737105641472 |
|---|---|
| author | Chen, Yang Zhang, Junzhe Yeo, Chai Kiat |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Chen, Yang Zhang, Junzhe Yeo, Chai Kiat |
| author_sort | Chen, Yang |
| collection | NTU |
| description | Knowledge transfer is critical in making use of data from multi-source domains, but most existing techniques are not privacy-preserving. Nowadays, data leakage, together with the advancement of big-data-driven Artificial Intelligence, has raised huge concerns over data security. The neglect of privacy makes such approaches impractical. For addressing intrusion detection tasks, the Deep Autoencoding Gaussian Mixture Model (DAGMM) concatenates and jointly optimizes a compression and an estimation network in an unsupervised manner. However, DAGMM still suffers from the lack of diversely distributed intrusion samples in real-life scenarios where organizations are neither willing nor legally allowed to engage in data sharing. Given the increasing public concern over data privacy and scandals, federated learning which only allows model parameter sharing is thus proposed to enhance model performance while preserving data privacy. Moreover, it also addresses the competitive concerns on the part of organizations when sharing data with their rivals. This study proposes a Federated Deep Autoencoding Gaussian Mixture Model (F-DAGMM) to build up privacy-preserving knowledge transfer, to further support inter-organizational cooperation and high-level decision making. A two-phase federated optimization strategy is proposed to address the performance degradation caused by the significant differences in the individual clients’ data distributions. Extensive experiments demonstrate the superiority of the proposed F-DAGMM. |
| first_indexed | 2025-02-19T03:58:51Z |
| format | Journal Article |
| id | ntu-10356/163890 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:58:51Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1638902022-12-21T05:17:08Z Privacy-preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model Chen, Yang Zhang, Junzhe Yeo, Chai Kiat School of Computer Science and Engineering Engineering::Computer science and engineering Knowledge Transfer Privacy Preserving Knowledge transfer is critical in making use of data from multi-source domains, but most existing techniques are not privacy-preserving. Nowadays, data leakage, together with the advancement of big-data-driven Artificial Intelligence, has raised huge concerns over data security. The neglect of privacy makes such approaches impractical. For addressing intrusion detection tasks, the Deep Autoencoding Gaussian Mixture Model (DAGMM) concatenates and jointly optimizes a compression and an estimation network in an unsupervised manner. However, DAGMM still suffers from the lack of diversely distributed intrusion samples in real-life scenarios where organizations are neither willing nor legally allowed to engage in data sharing. Given the increasing public concern over data privacy and scandals, federated learning which only allows model parameter sharing is thus proposed to enhance model performance while preserving data privacy. Moreover, it also addresses the competitive concerns on the part of organizations when sharing data with their rivals. This study proposes a Federated Deep Autoencoding Gaussian Mixture Model (F-DAGMM) to build up privacy-preserving knowledge transfer, to further support inter-organizational cooperation and high-level decision making. A two-phase federated optimization strategy is proposed to address the performance degradation caused by the significant differences in the individual clients’ data distributions. Extensive experiments demonstrate the superiority of the proposed F-DAGMM. Nanyang Technological University This work is supported in part by Grant No. NTU 04INS000471C130 and in part by the RIE2020 Industry Alignment Fund - Industry Collaboration Projects (IAF-ICP) Funding Initiative, as well as cash and in-kind contribution from Singapore Telecommunications Limited (Singtel), through Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU). 2022-12-21T05:17:08Z 2022-12-21T05:17:08Z 2022 Journal Article Chen, Y., Zhang, J. & Yeo, C. K. (2022). Privacy-preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model. Information Sciences, 609, 1204-1220. https://dx.doi.org/10.1016/j.ins.2022.07.104 0020-0255 https://hdl.handle.net/10356/163890 10.1016/j.ins.2022.07.104 2-s2.0-85135317535 609 1204 1220 en NTU 04INS000471C130 Information Sciences © 2022 Elsevier Inc. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Knowledge Transfer Privacy Preserving Chen, Yang Zhang, Junzhe Yeo, Chai Kiat Privacy-preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model |
| title | Privacy-preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model |
| title_full | Privacy-preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model |
| title_fullStr | Privacy-preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model |
| title_full_unstemmed | Privacy-preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model |
| title_short | Privacy-preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model |
| title_sort | privacy preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model |
| topic | Engineering::Computer science and engineering Knowledge Transfer Privacy Preserving |
| url | https://hdl.handle.net/10356/163890 |
| work_keys_str_mv | AT chenyang privacypreservingknowledgetransferforintrusiondetectionwithfederateddeepautoencodinggaussianmixturemodel AT zhangjunzhe privacypreservingknowledgetransferforintrusiondetectionwithfederateddeepautoencodinggaussianmixturemodel AT yeochaikiat privacypreservingknowledgetransferforintrusiondetectionwithfederateddeepautoencodinggaussianmixturemodel |