1,992 Hits in 2.9 sec

Spam Filtering

Kleanthi Georgala, Aris Kosmopoulos, George Paliouras
2014 Proceedings of the 4th International Conference on Web Intelligence, Mining and Semantics (WIMS14) - WIMS '14  
Use only 2% of the overall message labels  Consider natural grouping of data : select representative instances for training  ...   Unsupervised learning, based on local structure  Create groups of highly correlated data-points  No re-clustering of data  Our contribution : Active Learning combined with Incremental Clustering   ...  , X n } and a cluster C j,k of a clustering Cl j compute : Enron-Spam, NSCR "Demokritos"  Baseline : 2%B  Target Model : Supervised Training (ST)  Thresholds tested: [0.3,0.5], [0.5,1.0]  Evaluation  ... 
doi:10.1145/2611040.2611059 dblp:conf/wims/GeorgalaKP14 fatcat:qcet2r7jazgdtddp7qvrwa5acy

Semi Supervised Image Spam Hunter: A Regularized Discriminant EM Approach [chapter]

Yan Gao, Ming Yang, Alok Choudhary
2009 Lecture Notes in Computer Science  
It makes the cost too high for fully supervised learning to frequently collect sufficient labeled data for training.  ...  In this paper, we propose a semi-supervised approach, regularized discriminant EM algorithm (RDEM), to detect image spam emails, which leverages small amount of labeled data and large amount of unlabeled  ...  Most of them leverage supervised machine learning algorithms to build a classifier for filtering spam images [14, 15] by using image-based features.  ... 
doi:10.1007/978-3-642-03348-3_17 fatcat:x2xizupfa5gbhllzwnhev3b3je

Trends in Combating Image Spam E-mails [article]

Mohammadi Akheela Khanum, Lamia Mohammed Ketari
2012 arXiv   pre-print
Initially, spam e-mails contained only textual messages which were easily detected by the text-based spam filters.  ...  In this paper, we examine the motivations and the challenges in image spam filtering research, and we review the recent trends in combating image spam e-mails.  ...  The techniques listed in Table 1 uses supervised learning for training the classifiers. Few studies [21] have used semi-supervised learning techniques for image spam detection.  ... 
arXiv:1212.1763v1 fatcat:t3urvsj2b5dkjclap6poegdyuu

Semi-Supervised Spam Detection in Twitter Stream

Surendra Sedhai, Aixin Sun
2018 IEEE Transactions on Computational Social Systems  
In this paper, we propose a Semi-Supervised Spam Detection (S3D) framework for spam detection at tweet-level.  ...  Most existing techniques for spam detection on Twitter aim to identify and block users who post spam tweets.  ...  In this paper, we propose a semi-supervised framework for spam tweet detection.  ... 
doi:10.1109/tcss.2017.2773581 fatcat:nffhcngc7rgwlf3whjfnzxialq

Robust personalizable spam filtering via local and global discrimination modeling

Khurum Nazir Junejo, Asim Karim
2012 Knowledge and Information Systems  
E-mail service providers have two options for automatic spam filtering at the service-side: a single global filter for all users or a personalized filter for each user.  ...  The results demonstrate the robustness and effectiveness of our filter and its suitability for global and personalized spam filtering at the service-side.  ...  We would also like to thank the anonymous reviewers for their helpful feedback.  ... 
doi:10.1007/s10115-012-0477-x fatcat:uwnwycedwjc2lm4oeue5cigvca

A Comprehensive Survey for Intelligent Spam Email Detection

Asif Karim, Sami Azam, Bharanidharan Shanmugam, Krishnan Kannoorpatti, Mamoun Alazab
2019 IEEE Access  
The tremendously growing problem of phishing e-mail, also known as spam including spear phishing or spam borne malware, has demanded a need for reliable intelligent anti-spam e-mail filters.  ...  INDEX TERMS Machine learning, phishing attack, spear phishing, spam detection, spam email, spam filtering. VOLUME 7, 2019 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  Semi-supervised spam filtering systems have also demonstrated promise, even though not many attempts have been taken to construct such systems yet.  ... 
doi:10.1109/access.2019.2954791 fatcat:ikt6cayggbb2dkrm52fxzz2dqm

An ensemble of cluster-based classifiers for semi-supervised classification of non-stationary data streams

Mohammad Javad Hosseini, Ameneh Gholipour, Hamid Beigy
2015 Knowledge and Information Systems  
In this paper, we propose an ensemble algorithm to classify instances of non-stationary data streams in a semi-supervised environment.  ...  This e-offprint is for personal use only and shall not be self-archived in electronic repositories.  ...  Acknowledgments The authors would like to thank the anonymous reviewers for their valuable comments and suggestions which improved the paper.  ... 
doi:10.1007/s10115-015-0837-4 fatcat:xo66au7lpvd6bivc6uw3rhuwva

A Study on Spam Detection Methods for Safe SMS Communication

Shailee Bhatia, . .
2018 International Journal of Engineering & Technology  
The paper has explored the types of SMS spams, its threats and various filtration methods to detect the spam SMS.  ...  Spam messages not only involves the unwanted messages but it also includes some viruses and threat to the security system. In this paper, a study to the SMS filtration methods is provided.  ...  Author [11] has used the cluster adaptive method for semi-supervised analysis for spam message detection.  ... 
doi:10.14419/ijet.v7i3.12.16502 fatcat:ni53wyzmffcadca2ghrxginery

Semi-supervised Classification for Natural Language Processing [article]

Rushdi Shams
2014 arXiv   pre-print
This study explores the possibilities and achievements as well as complexity and limitations of semi-supervised classification for several natural langue processing tasks like parsing, biomedical information  ...  For instance, supervised classification exploits only labeled data that are expensive, often difficult to get, inadequate in quantity, and require human experts for annotation.  ...  The results in 2006 ECML/PKDD spam discovery challenge [10] indicated that spam filters based on semi-supervised classification outperformed supervised filters.  ... 
arXiv:1409.7612v1 fatcat:r2qppm2xcbcm3o5hlzgjrkzube

A Machine Learning Method for Spam Detection in Twitter using Naive Bayes and ERF Algorithms

To combat with the issue of spams, there has been a lot of methods available, Yet, there is not a perfect effective solution for detect the Twitter spams with the exactness.  ...  The vast increase in the popularity in the social media also makes the hackers to spam, thus causes the conceivable losses.  ...  It is a kind of stream clustering which filter the spam by categorising tweets as spam and non spam clusters. In Stream clustering methods which cluster may have number of micro clusters.  ... 
doi:10.35940/ijitee.f4729.049620 fatcat:eghpqql7mzbqxmtym5yqeivjie

SoK: Applying Machine Learning in Security - A Survey [article]

Heju Jiang, Jasvir Nagra, Parvez Ahammad
2016 arXiv   pre-print
Our examinations lead to 1) a taxonomy on ML paradigms and security domains for future exploration and exploitation, and 2) an agenda detailing open and upcoming challenges.  ...  Consequently, research on applying and designing ML algorithms and systems for security has grown fast, ranging from intrusion detection systems(IDS) and malware classification to security policy management  ...  Mostly using supervised learning paradigm, NB, SVM with different kernels, and LR are popular ML classifiers for filtering spam and phishing.  ... 
arXiv:1611.03186v1 fatcat:hfvc5hhu7ze77lrnjufslcg6gm

PSSF: A Novel Statistical Approach for Personalized Service-side Spam Filtering

Khurum Nazir Junejo, Asim Karim
2007 IEEE/WIC/ACM International Conference on Web Intelligence (WI'07)  
Since the distribution of spam and non-spam e-mails is often different for different users a single filter trained on a general corpus is not optimal for all users.  ...  We address this question by presenting PSSF, a novel statistical approach for personalized service-side spam filtering.  ...  Cheng and Li present a semi-supervised classifier ensemble approach for the personalized spam filtering problem [4] .  ... 
doi:10.1109/wi.2007.47 dblp:conf/webi/JunejoK07 fatcat:wrbo2zidazbefnvumr52f2yl5y

An Improved Feature Selection Method for Short Text Classification

Olusola Abayomi-Alli, Sanjay Misra, Victor O Matthews, Modupe Odusami, Adebayo Abayomi-Alli, Ravin Ahuja, Rytis Maskeliunas
2019 Journal of Physics, Conference Series  
Thus, a modified Genetic Algorithm (GA) for improve feature selection and Artificial Immune System (AIS) algorithm was proposed for effective text classification in mobile short messages.  ...  The exponential growth of text documents shared among users globally has increased the threat of misclassification associated with mobile devices such as Spam, Phishing, License to kill, Malware and privacy  ...  Authors [4] improved text classification using semi-supervised clustering approach. The method uses labeled text for clustering and unlabeled text was used to adapt to centroids.  ... 
doi:10.1088/1742-6596/1235/1/012021 fatcat:abskwxcawrg2hdmrujmhypnjei

Automatic Personalized Spam Filtering through Significant Word Modeling

Khurum Naz Junejo, Asim Karim
2007 19th IEEE International Conference on Tools with Artificial Intelligence(ICTAI 2007)  
We present an automatic approach for personalized spam filtering that does not require users' feedback.  ...  A personalized spam filter is built by taking into account the characteristics of e-mails in individual users' inboxes.  ...  Cheng and Li present a semi-supervised classifier ensemble approach for the personalized spam filtering problem [19] .  ... 
doi:10.1109/ictai.2007.66 dblp:conf/ictai/JunejoK07 fatcat:ucyps6ixrnfk5jexny66sar75i


Saini Jacob Soman, S. Murugappan
2014 Journal of Computer Science  
The growing popularity of social networking sites has made them prime targets for spammers.  ...  Therefore, this study attempts to review various spam detection frameworks which deals about the detection and elimination of spams in various sources.  ...  Here, spam comment is an irrelevant response received for a blog post in the form of a comment. This comments are analyzed using supervised and semi supervised methods.  ... 
doi:10.3844/jcssp.2014.2135.2140 fatcat:56u4f2hs75gdbl2w5yjyoagfym
« Previous Showing results 1 — 15 out of 1,992 results