Project deliverable Open Access

Machine Learning empowered intrusion detection using Honeypots' data v1

Dr Serafeim Moustakidis

Citation Style Language JSON Export

  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.3935784", 
  "language": "eng", 
  "title": "Machine Learning empowered intrusion detection using Honeypots' data v1", 
  "issued": {
    "date-parts": [
  "abstract": "<p>This deliverable presents the overall development status of the Machine Learning Intrusion Detection (MLID) component on M18 of the project&rsquo;s lifetime and the end of the first interim of MLID&rsquo;s two-staged development phases (M10-M18, M22-M30). This is a versioned document and describes the progress of the development of the first prototype of the component. Within the first development phase of MLID, feature exploration has been performed and a list of the most informative features (reflecting different aspects of users&rsquo; behaviour) has been identified. Three AI pipelines for intrusion detection have been designed, developed and evaluated in an extensive comparative analysis that includes multiple variants of each pipeline with numerous machine leaning (ML) and deep learning (DL) models.&nbsp;</p>", 
  "author": [
      "family": "Dr Serafeim Moustakidis"
  "version": "1.0", 
  "type": "report", 
  "id": "3935784"
All versions This version
Views 8888
Downloads 7070
Data volume 241.0 MB241.0 MB
Unique views 7575
Unique downloads 6161


Cite as