59 Hits in 2.7 sec

Multi-Language Spam/Phishing Classification by Email Body Text: Toward Automated Security Incident Investigation

Justinas Rastenis, Simona Ramanauskaitė, Ivan Suzdalev, Kornelija Tunaitytė, Justinas Janulevičius, Antanas Čenys
2021 Electronics  
Therefore this paper presents a solution, based on email message body text automated classification into spam and phishing emails.  ...  Spamming and phishing are two types of emailing that are annoying and unwanted, differing by the potential threat and impact to the user.  ...  Meanwhile, phishing emails seek to mimic legitimate emails and influence the user to execute some intended actions and reveal their personal information.  ... 
doi:10.3390/electronics10060668 fatcat:2sqbhq52jbhf7i2kccfr6hts3i

An incremental cluster-based approach to spam filtering

Wen-Feng Hsiao, Te-Min Chang
2008 Expert systems with applications  
A cluster-based classification method, called ICBC, is developed accordingly. ICBC contains two phases.  ...  As email becomes a popular means for communication over the Internet, the problem of receiving unsolicited and undesired emails, called spam or junk mails, severely arises.  ...  The predictive threshold was used to determine whether Magi should provide its suggested action to the user for reference or not.  ... 
doi:10.1016/j.eswa.2007.01.018 fatcat:f27qosx7wrd73iyovr7ksjlw2m

Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice [article]

David Watson, Limor Gultchin, Ankur Taly, Luciano Floridi
2021 arXiv   pre-print
Building on work in logic, probability, and causality, we establish the central role of necessity and sufficiency in XAI, unifying seemingly disparate methods in a single formal framework.  ...  provide a sound and complete algorithm for computing explanatory factors with respect to a given context, and demonstrate its flexibility and competitive performance against state of the art alternatives on  ...  We report results based on 50 randomly sampled inputs from the Adult dataset, where references are fixed by conditioning on the opposite prediction.  ... 
arXiv:2103.14651v2 fatcat:ptuvien33zbwxn5e4v2u75kaj4

An adaptive personalized news dissemination system

Ioannis Katakis, Grigorios Tsoumakas, Evangelos Banos, Nick Bassiliades, Ioannis Vlahavas
2008 Journal of Intelligent Information Systems  
In this work, we bridge theory to practice, by implementing a web-based news reader enhanced with a specifically designed machine learning framework for dynamic content personalization.  ...  PersoNews is freely available for public use on the WWW (  ...  Server-based systems will have to maintain at least one personal classifier for every user.  ... 
doi:10.1007/s10844-008-0053-8 fatcat:zwyvnbvj75fojn3fyrondpgmga

Email Spam Filtering: A Systematic Review

Gordon V. Cormack
2008 Foundations and Trends in Information Retrieval  
A typical email user has a working definition no more formal than "I know it when I see it."  ...  We survey current and proposed spam filtering techniques with particular emphasis on how well they work.  ...  Tests of common filters on public and private email collections indicate that results achieved on the public datasets predict well those on private ones representing real sequences of email.  ... 
doi:10.1561/1500000006 fatcat:rdmysuohjbd5de54ktguwsoqum

PhishOut: Effective Phishing Detection Using Selected Features [article]

Suhail Paliath, Mohammad Abu Qbeitah, Monther Aldwairi
2020 arXiv   pre-print
We study the feature effectiveness based on Information Gain and contribute two new features to the literature.  ...  We compare six machine-learning approaches to detect phishing based on a small number of carefully chosen features.  ...  Phishing forms Based on the techniques used to deliver attacks or steal personal information, we divide the phishing attacks into the following groups [12] . 1) F irst group is link-based. 2) Second group  ... 
arXiv:2004.09789v1 fatcat:wwxguchf6rdc7br7mrih6wihpy

A lifelong spam emails classification model

Rami Mustafa A. Mohammad
2020 Applied Computing and Informatics  
Yet, spammers know that the longer they will use the same set of features for tricking email users the more probably the anti-spam parties might develop tools for combating this kind of annoying email  ...  Spam emails classification using data mining and machine learning approaches has enticed the researchers' attention duo to its obvious positive impact in protecting internet users.  ...  his ID. 4-Tagging the email as a probable spam and provide it to the end user in order to choose the proper action.  ... 
doi:10.1016/j.aci.2020.01.002 fatcat:biwpczx3zveshf2ug4dmjz7iiy

Tutorial and critical analysis of phishing websites methods

Rami M. Mohammad, Fadi Thabtah, Lee McCluskey
2015 Computer Science Review  
This research will mostly focus on the web based phishing detection methods rather than email based detection methods.  ...  On the other hand, phishing emails are sent to get your personal information, which will be used later in fraud activities.  ...  This research will mostly focus on the web based phishing detection methods rather than email based detection methods.  ... 
doi:10.1016/j.cosrev.2015.04.001 fatcat:dcbl7izcufd5rkfq26rvr2dbdm

A Knowledge Acquisition Method of Judgment Rules for Spam E-mail by using Self Organizing Map and Automatically Defined Groups by Genetic Programming [chapter]

Takumi Ichimura, Kazuya Mera, Akira Har
2010 Self-Organizing Maps  
The rule must be redefined by each user according to user's work style and so on.  ...  In this paper, we propose a classification method for Spam E-mail based on the results of SpamAssassin, which is the open source software to identify spam signatures.  ... 
doi:10.5772/9177 fatcat:bwfvt53lyvexheiyntnkqr32jy

Phishing Email Detection Using Natural Language Processing Techniques: A Literature Survey

Said Salloum, Tarek Gaber, Sunil Vadera, Khaled Shaalan
2021 Procedia Computer Science  
On the other hand, phishing emails have increased exponentially in recent years, which suggests a need for more effective and advanced methods to counter them.  ...  On the other hand, phishing emails have increased exponentially in recent years, which suggests a need for more effective and advanced methods to counter them.  ...  Accordingly, such techniques are based on the use of ML-based approaches as well as ML-based evaluation metrics.  ... 
doi:10.1016/j.procs.2021.05.077 fatcat:xiypnoobzfdn3h7ggopppaxdnq

Spam Filtering using K mean Clustering with Local Feature Selection Classifier

Anand Sharma, Vedant Rastogi
2014 International Journal of Computer Applications  
In this paper, we present a comprehensive review of recent developments in the application of machine learning algorithms to Spam filtering, focusing on textual approaches.  ...  filtering term selection we are using Document frequency method, for feature extraction we are using bag of words model for classification we are using k-mean clustering method along with local concentration based  ...  Similarly, non-spam email should be avoided for personal email communications between users, and limit any forms of bulk mailings, regardless of whether they were solicited or not.  ... 
doi:10.5120/18951-0096 fatcat:oolxaa4awnc63nvrlobv3652yq

Creative Persuasion: A Study on Adversarial Behaviors and Strategies in Phishing Attacks

Prashanth Rajivan, Cleotilde Gonzalez
2018 Frontiers in Psychology  
In the end-user phase, 340 participants performed an email management task, where they examined and classified phishing emails generated by participants in phase-one along with benign emails.  ...  Data from both phases of the study was combined and analyzed, to measure the effect of adversarial behaviors on end-user response to phishing emails.  ...  People may be more averse to accept failure and more willing to take actions on emails that involve possible losses.  ... 
doi:10.3389/fpsyg.2018.00135 pmid:29515478 pmcid:PMC5826381 fatcat:dxzgxypbbra3dbdlsmbbk5tgle

Beyond blacklists

Justin Ma, Lawrence K. Saul, Stefan Savage, Geoffrey M. Voelker
2009 Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '09  
In this paper, we describe an approach to this problem based on automated URL classification, using statistical methods to discover the tell-tale lexical and host-based properties of malicious Web site  ...  As a result, there has been broad interest in developing systems to prevent the end user from visiting such sites.  ...  Acknowledgments Thanks go to Alvin AuYoung, Kirill Levchenko, Patrick Verkaik and Michael Vrable for insightful comments on earlier drafts of this paper.  ... 
doi:10.1145/1557019.1557153 dblp:conf/kdd/MaSSV09 fatcat:iqalo4necnbrrogpkjhbc36ei4

Machine learning for email spam filtering: review, approaches and open research problems

Emmanuel Gbenga Dada, Joseph Stephen Bassi, Haruna Chiroma, Shafi'i Muhammad Abdulhamid, Adebayo Olusola Adetunmbi, Opeyemi Emmanuel Ajibuwa
2019 Heliyon  
We present a systematic review of some of the popular machine learning based email spam filtering approaches.  ...  Discussion on general email spam filtering process, and the various efforts by different researchers in combating spam through the use machine learning techniques was done.  ...  A good example of a rule based spam filter is SpamAssassin [35] .  ... 
doi:10.1016/j.heliyon.2019.e01802 pmid:31211254 pmcid:PMC6562150 fatcat:n7qiq4tgnzh7xi6j5c2ah335hy

A Comprehensive Overview on Cybersecurity: Threats and Attacks

Preetha S, P. Lalasa, Pradeepa R
International Data Corporation predicts that global spending on cybersecurity solutions will reach $133.7 billion by 2022 as cyber threats continue to increase.  ...  When an email is received by the user, filtering function is performed by the spam filter and checks whether the message is spam. Based on the URL reputation of the email Spam filtering is done.  ...  Using datasets collected from HamCorpus (legitimate email) of SpamAssassin project and publicly available PhishingCorpus (phishing email) assessment was done.  ... 
doi:10.35940/ijitee.h9242.0610821 fatcat:s46wfv2e4ffcjm53cjwqznk43e
« Previous Showing results 1 — 15 out of 59 results