Intrusion Detection Using Federated Learning

G. K. Sudhina Kumar, K. Krishna Prakasha, Balachandra Muniyal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)


In the evolving world, the drastic expansion of the internet and the use of smart devices demands a change in existing infrastructure. These rapid changes in the structural level also open new dimensions that are susceptible to cyber-attacks. One of the efficient methods to tackle these situations is to apply intelligence to the systems and detect abnormal behaviours. As privacy plays a vital role, here Federated Learning method is used to detect cyber attacks by analysing the data logs and compared with the non-federated learning techniques on the same data. It is very evident from the experiment that Federated Learning is very effective in detecting these attacks by preserving the privacy of the victim organisations/systems.

Original languageEnglish
Title of host publicationApplications and Techniques in Information Security - 13th International Conference, ATIS 2022, Revised Selected Papers
EditorsSrikanth Prabhu, Shiva Raj Pokhrel, Gang Li
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages9
ISBN (Print)9789819922635
Publication statusPublished - 2023
Event13th International Conference on Applications and Techniques in Information Security, ATIS 2022 - Manipal, India
Duration: 30-12-202231-12-2022

Publication series

NameCommunications in Computer and Information Science
Volume1804 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937


Conference13th International Conference on Applications and Techniques in Information Security, ATIS 2022

All Science Journal Classification (ASJC) codes

  • General Computer Science
  • General Mathematics


Dive into the research topics of 'Intrusion Detection Using Federated Learning'. Together they form a unique fingerprint.

Cite this