dc.creator | Papafotikas S., Kakarountas A. | en |
dc.date.accessioned | 2023-01-31T09:42:53Z | |
dc.date.available | 2023-01-31T09:42:53Z | |
dc.date.issued | 2019 | |
dc.identifier | 10.1109/SEEDA-CECNSM.2019.8908520 | |
dc.identifier.isbn | 9781728147574 | |
dc.identifier.uri | http://hdl.handle.net/11615/77652 | |
dc.description.abstract | Nowadays we see the sharp increase in smart devices on the internet and in the network of things. An ever increasing problem with these devices is their protection against malware and internet attacks because of their heterogeneity. This makes them vulnerable and many of them without even showing signs of malfunction. In this work, we study these devices, the types of attacks that make them vulnerable, and suggest a digital system that embeds a Machine Learning(ML)-based clustering algorithm for detecting suspicious behavior, exploiting current supply characteristic dissipation. The system is prototype and uses the K-Means Clustering Algorithm with Supervised Training. The results of this work showed successful detection of suspicious behavior of smart IoT devices. © 2019 IEEE. | en |
dc.language.iso | en | en |
dc.source | 2019 4th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference, SEEDA-CECNSM 2019 | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85076353845&doi=10.1109%2fSEEDA-CECNSM.2019.8908520&partnerID=40&md5=398ab094e0e7f020e64b1fd290049d47 | |
dc.subject | Computer aided design | en |
dc.subject | Digital devices | en |
dc.subject | Intrusion detection | en |
dc.subject | K-means clustering | en |
dc.subject | Machine learning | en |
dc.subject | Malware | en |
dc.subject | Social networking (online) | en |
dc.subject | Component | en |
dc.subject | Formatting | en |
dc.subject | Insert | en |
dc.subject | Style | en |
dc.subject | Styling | en |
dc.subject | Internet of things | en |
dc.subject | Institute of Electrical and Electronics Engineers Inc. | en |
dc.title | A machine-learning clustering approach for intrusion detection to IoT devices | en |
dc.type | conferenceItem | en |