Spam Email Clustering by Ordered Pair of Modality: 2023 15th International Congress on Advanced Applied Informatics Winter (IIAI-AAI-Winter)
Takeshi Matsuda, Takeshi Fujimaki, Michio Sonoda · 2023
Cyber-attacks that deceive people in various ways, such as phishing scams that exploit personal information by pretending to be a real service, are gaining momentum. Scam email sometimes includes important keywords that are cleverly used to deceive people, but not always. This study focused on the modality representation contained in scam emails that make people uneasy and defined order pair of modality representation of 100 dimensions. Furthermore, we applied a dimensionality reduction algorithm to verify the accuracy of unsupervised learning of scam and normal em ails.