公开(公告)号：US10404745B2

公开(公告)日：2019-09-03

申请号：US15225587

申请日：2016-08-01

申请人： Rakesh Verma ,  Narasimha Karpoor Shashidhar ,  Nabil Hossain ,  Nirmala Rai

发明人： Rakesh Verma ,  Narasimha Karpoor Shashidhar ,  Nabil Hossain ,  Nirmala Rai

IPC分类号： H04L29/06 ,  H04L12/58 ,  G06N20/00

摘要： A comprehensive scheme to detect phishing emails using features that are invariant and fundamentally characterize phishing. Multiple embodiments are described herein based on combinations of text analysis, header analysis, and link analysis, and these embodiments operate between a user's mail transfer agent (MTA) and mail user agent (MUA). The inventive embodiment, PhishNet-NLP™, utilizes natural language techniques along with all information present in an email, namely the header, links, and text in the body. The inventive embodiment, PhishSnag™, uses information extracted form the embedded links in the email and the email headers to detect phishing. The inventive embodiment, Phish-Sem™ uses natural language processing and statistical analysis on the body of labeled phishing and non-phishing emails to design four variants of an email-body-text only classifier. The inventive scheme is designed to detect phishing at the email level.

公开(公告)号：US20160344770A1

公开(公告)日：2016-11-24

申请号：US15225587

申请日：2016-08-01

申请人： Rakesh Verma ,  Narasimha Karpoor Shashidhar ,  Nabil Hossain ,  Nirmala Rai

发明人： Rakesh Verma ,  Narasimha Karpoor Shashidhar ,  Nabil Hossain ,  Nirmala Rai

IPC分类号： H04L29/06 ,  G06N99/00 ,  H04L12/58

CPC分类号： H04L63/1483 ,  G06N20/00 ,  H04L51/22

摘要： A comprehensive scheme to detect phishing emails using features that are invariant and fundamentally characterize phishing. Multiple embodiments are described herein based on combinations of text analysis, header analysis, and link analysis, and these embodiments operate between a user's mail transfer agent (MTA) and mail user agent (MUA). The inventive embodiment, PhishNet-NLP™, utilizes natural language techniques along with all information present in an email, namely the header, links, and text in the body. The inventive embodiment, PhishSnag™, uses information extracted form the embedded links in the email and the email headers to detect phishing. The inventive embodiment, Phish-Sem™ uses natural language processing and statistical analysis on the body of labeled phishing and non-phishing emails to design four variants of an email-body-text only classifier. The inventive scheme is designed to detect phishing at the email level.

摘要翻译： 一个全面的方法来检测网络钓鱼电子邮件，这些功能是不变的，从根本上讲是网络钓鱼的特征。 本文基于文本分析，头部分析和链接分析的组合来描述多个实施例，并且这些实施例在用户的邮件传送代理（MTA）和邮件用户代理（MUA）之间进行操作。 本发明的实施例PhishNet-NLP TM利用自然语言技术以及电子邮件中存在的所有信息，即身体中的标题，链接和文本。 本发明的实施例PhishSnag TM使用从电子邮件中的嵌入式链接提取的信息和电子邮件头来检测网络钓鱼。 本发明的实施例，Phish-Sem™使用自动语言处理和统计分析标签的网络钓鱼和非网络钓鱼电子邮件的身体来设计电子邮件 - 正文文本分类器的四个变体。 本发明的方案旨在检测电子邮件级的钓鱼。

公开(公告)号：US20150067833A1

公开(公告)日：2015-03-05

申请号：US14015524

申请日：2013-08-30

申请人： Narasimha Shashidhar ,  Nabil Hossain ,  Rakesh Verma

发明人： Rakesh Verma ,  Narasimha Karpoor Shashidhar ,  Nabil Hossain

IPC分类号： H04L29/06

CPC分类号： H04L63/1483

摘要： A comprehensive scheme to detect phishing emails using features that are invariant and fundamentally characterize phishing. Multiple embodiments are described herein based on combinations of text analysis, header analysis, and link analysis, and these embodiments operate between a user's mail transfer agent (MTA) and mail user agent (MUA). The inventive embodiment, PhishNet-NLP™, utilizes natural language techniques along with all information present in an email, namely the header, links, and text in the body. The inventive embodiment, PhishSnag™, uses information extracted form the embedded links in the email and the email headers to detect phishing. The inventive embodiment, Phish-Sem™ uses natural language processing and statistical analysis on the body of labeled phishing and non-phishing emails to design four variants of an email-body-text only classifier. The inventive scheme is designed to detect phishing at the email level.

摘要翻译： 一个全面的方法来检测网络钓鱼电子邮件，这些功能是不变的，从根本上讲是网络钓鱼的特征。 本文基于文本分析，头部分析和链接分析的组合来描述多个实施例，并且这些实施例在用户的邮件传送代理（MTA）和邮件用户代理（MUA）之间进行操作。 本发明的实施例PhishNet-NLP TM利用自然语言技术以及电子邮件中存在的所有信息，即身体中的标题，链接和文本。 本发明的实施例PhishSnag TM使用从电子邮件中的嵌入式链接提取的信息和电子邮件头来检测网络钓鱼。 本发明的实施例，Phish-Sem™使用自动语言处理和统计分析标签的网络钓鱼和非网络钓鱼电子邮件的身体来设计电子邮件 - 正文文本分类器的四个变体。 本发明的方案旨在检测电子邮件级的钓鱼。