Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/6D93408B-9D4E-4ECC-B239-1D71844363BF | ||
| Year | 2022 | ||
| Type of Item | Master Thesis | ||
| License |
|
||
| Bibliographic Citation | Themistoklis Chasiotis, "Machine learning practices for Cybersecurity", Master Thesis, School of Production Engineering and Management, Technical University of Crete, Hellenic Army Academy, Chania, Greece, 2022 https://doi.org/10.26233/heallink.tuc.94671 | ||
| Appears in Collections |
This thesis studies artificial intelligence tools for early and effective threat identification, prioritization and deterrence in order to develop software systems to support cyber threat assessment and response decisions.The topics explored in this thesis include anomaly-based network intrusion detection, insider threat detection, spam and phishing detection, behavior-based malware detection, and malware detection activity based on parsing machine language commands etc.The AI methods offered for this purpose include machine learning for software analysis, machine learning and data mining for database security, machine learning for malware detection and more. A source of particularly significant problems is the fact that artificial intelligence algorithms are necessarily trained on a limited set of examples, since malware behavior is unknown and rapidly changing.Finally presents the main classification and clustering principles in the case of supervised learning. Then different data sets were processed to perform malware detection and finally the detection and identification of different cyber attacks is presented.
Copyright © DIAS 2013
