A Machine-Learning Approach to Phishing Detection and Defense
Auteurs : Akanbi O.A., Amiri Iraj Sadegh, Fazeldehkordi E.
- Introduction
- Literature Review
- Research Methodology
- Feature Extraction
- Implementation and Result
- Conclusions
Dr. Iraj Sadegh Amiri received his B. Sc (Applied Physics) from Public University of Urmia, Iran in 2001 and a gold medalist M. Sc. in optics from University Technology Malaysia (UTM), in 2009. He was awarded a PhD degree in photonics in Jan 2014. He has published well over 350 academic publications since the 2012s in optical soliton communications, laser physics, photonics, optics and nanotechnology engineering. Currently he is a senior lecturer in University of Malaysia (UM), Kuala Lumpur, Malaysia.
E. Fazeldehkordi received her Associate’s Degree in Computer Hardware from the University of Science and Technology, Tehran, Iran, B. Sc (Electrical Engineering-Electronics) from Azad University of Tafresh, Iran, and M. Sc. in Information Security from Universiti Teknologi Malaysia (UTM). She currently conducts research in information security and has recently published her research on Mobile Ad Hoc Network Security using CreateSpace.
- Discover novel research into the uses of machine-learning principles and algorithms to detect and prevent phishing attacks
- Help your business or organization avoid costly damage from phishing sources
- Gain insight into machine-learning strategies for facing a variety of information security threats
Date de parution : 12-2014
Ouvrage de 100 p.
15.2x22.8 cm
Thèmes d’A Machine-Learning Approach to Phishing Detection and... :
Mots-clés :
accuracy; algorithm; anti-phishing; blacklist; classification; classifier; classifiers; confidentiality; cross-validation; cybersecurity; dataset; email; ensemble; ensemble; detection; false alarm; false alarm rates; false negatives; feature extraction; fraud; information; nonphishing; performance; performance metrics; phishing; Phishtank; preprocessing; threat; true negative; true positive; voting; website; websites