In this thesis, we exploit the advantages of Machine learning (ML) in the domains of data security and data privacy. ML is one of the most exciting technologies being developed in the world today. The major advantages of ML technology are its prediction capability and its ability to reduce the need for human activities to perform tasks. These benefits motivated us to exploit ML to improve users' data privacy and security. Firstly, we use ML technology to try to predict the best privacy settings for users, since ML has a strong prediction ability and the average user might find it difficult to properly set up privacy settings due to a lack of knowledge and subsequent lack of decision-making abilities regarding the privacy of their data. Besides, since the ML approach has the potential to considerably cut down on manual efforts by humans, our second task in this thesis is to exploit ML technology to redesign security mechanisms of social media environments that rely on human participation for providing such services. In particular, we use ML to train spam filters for identifying and removing violent, insulting, aggressive, and harassing content creators (a.k.a. spammers) from a social media platform. It helps to solve violent and aggressive issues that have been growing on social media environments. The experimental results show that our proposals are efficient and effective.

Enhancing data privacy and security related process through machine learning / Alom, Md Zulfikar. - (2019).

Enhancing data privacy and security related process through machine learning

Alom, Md Zulfikar
2019-01-01

Abstract

In this thesis, we exploit the advantages of Machine learning (ML) in the domains of data security and data privacy. ML is one of the most exciting technologies being developed in the world today. The major advantages of ML technology are its prediction capability and its ability to reduce the need for human activities to perform tasks. These benefits motivated us to exploit ML to improve users' data privacy and security. Firstly, we use ML technology to try to predict the best privacy settings for users, since ML has a strong prediction ability and the average user might find it difficult to properly set up privacy settings due to a lack of knowledge and subsequent lack of decision-making abilities regarding the privacy of their data. Besides, since the ML approach has the potential to considerably cut down on manual efforts by humans, our second task in this thesis is to exploit ML technology to redesign security mechanisms of social media environments that rely on human participation for providing such services. In particular, we use ML to train spam filters for identifying and removing violent, insulting, aggressive, and harassing content creators (a.k.a. spammers) from a social media platform. It helps to solve violent and aggressive issues that have been growing on social media environments. The experimental results show that our proposals are efficient and effective.
2019
Machine learning, Internet of Things, privacy preferences, privacy policies, context awareness, spam detection, social network security
Enhancing data privacy and security related process through machine learning / Alom, Md Zulfikar. - (2019).
File in questo prodotto:
File Dimensione Formato  
PhD_Thesis_AlomMdZulfikar_completa.pdf

accesso aperto

Descrizione: testo completo tesi
Tipologia: Tesi di dottorato
Licenza: Non specificato
Dimensione 2.27 MB
Formato Adobe PDF
2.27 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11383/2090627
 Attenzione

L'Ateneo sottopone a validazione solo i file PDF allegati

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact