Spam Filtering Research Articles

Spam Detection and Spammer Behaviour Analysis in Twitter Using Content Based Filtering Approach

Twitter is one of the most popular social media networks and therefore it is prone to misuse. One of the ways in which people misuse Twitter is by spamming. Spam becomes an issue once a communication medium especially one, which enables global communication and handle huge amount of online data. Since Twitter is popular among so many people, it makes it easy for spammers to thrive. Spammers are people who send unwanted messages to people to either advertise a product or lure the victims into clicking malicious links, which may affect their user systems. The main objective of these spammers is usually to make money from their victims. In the last years, several systems has-been made with the aim of determining whether a user is a spammer or not. However, these systems cannot filter each spam message and a different account can be created by a spammer and used to send other messages. This paper proposes a content-based approach, which can be used to filter spam tweets. The approach involves using tweets in machine learning and compression algorithms in order to filter the undesired tweets.

Detection and Prevention of Spam Mail with Semantics-based text classification of Collaborative and Content Filtering

Eventhough, conventional technologies are quiet good in separating spam messages, still soo many measures have to be considered to make more accuracy in spam filtering. In this work, we worked towards detecting spam mails and filtering it during its transmission. We proposed Collaborative filtering approach hybrid with text classification (semantics based). The related feature are retrieved from the text content. Also, another filtering method known as Content-based filtering is proposed which filters the same spam mail with more precision and better accuracy. Along with the semantic texts the Content-based filtering filters the special symbols such as HTML tags, @,/etc. Results are compared and the accuracy of detecting spam e-mails of Content-based filters is more than that of Collaborative filters. Both Collaborative and Content-based filters perform keyword check available in the spam keyword database and detects whether the mail sent by the sender is genuine or spam. Genuine emails are sent successfully and the spam emails are blocked at the server side. Content-based email classification requires an understanding of both structural and semantic attributes of email. Conventional research is focussed on semantic properties through structural components of email. After analysing the emails as events (as a major subset of the class of email), a rich contextual test-bed representation for an understanding of the semantic attributes of emails has been devised. The event-based emails have traditionally been studied based on simple structural properties.

WITHDRAWN: An effective approach to protect social media account from spam mail – A machine learning approach

The internet users in the world are rising rapidly. This technology given the opportunities to grow in the field of business, education, sports, entertainment and social media. With a huge amount of person getting connected to Internet, the security threats which leads massive harms are increasing also. In the last few years, we have been observing a quick development in information being produced and shared in social media. The usage of social media increased exponentially, and rapid growth of users are unexpected in the history of technology insurgency. The uninterrupted growth in social media and connected technologies has managed to an ecosystem where users with different culture and geolocation are connected on various social media platforms. While the explosive growth of internet users in Social Media results a high risk for user’s data due to cyber security breaches and data theft. Now a days, hackers use spam emails to data theft of social media’s profile. They send the spam mails with malicious links, after clicking on the link, details of the profiles are sent to hackers. In this Paper, we discuss the various steps taken to protect the social media profile and propose spam filter using decision tree model. We compare the testing and training accuracy of various algorithms on the emails_small and emails_full datasets and try to explain which one is better with different dataset. We evaluate the performance of Decision Tree (DT) based classifier with Information gain criterion which achieve accuracy 90% and Gini impurity criterion which achieve accuracy 89%. Evaluate the ROC curves for DT and K-Nearest Neighbors (KNN) classifier over emails_full dataset to test the idea of the classifier quality and can be used to quantify the area under the curve.

Genealogies of online content identification - an introduction

In today’s digital landscape, cultural content such as texts, films, images, and recorded sounds are increasingly subjected to automatic (or semi-automatic) processes of identification and classification. On a daily basis, spam filters scan swaths of emails in order to separate legit and illegitimate textual messages (Brunton, 2013), algorithms analyze years of user-uploaded film on YouTube in search for copyright violations (Heuguet, 2019), and software systems are deployed to scrutinize millions of images on social media sites in order to detect sexually offensive content (Liao, 2018). These examples reveal how machines and algorithmic systems are increasingly utilized to make complex judgments regarding cultural content. Indeed, it could be argued that the wide-ranging adoption of content identification systems is constructing new ontologies of culture and regimes of truth in the online domain. When put to action, content identification systems are trusted with the ability to separate good/bad and legal/illegal forms of communication and used to secure the singularity, value, authenticity, origin, and ownership of content. Such efforts are deeply embedded in constructions of knowledge, new forms of political governance, and not least global market transactions. Content identification tools now make up an essential part of the online data economy by protecting the interests of rights holders and forwarding the mathematization, objectification, and commodification of cultural productions.

Research Trends in Network-Based Intrusion Detection Systems: A Review

Network threats and hazards are evolving at a high-speed rate in recent years. Many mechanisms (such as firewalls, anti-virus, anti-malware, and spam filters) are being used as security tools to protect networks. An intrusion detection system (IDS) is also an effective and powerful network security system to detect unauthorized and abnormal network traffic flow. This article presents a review of the research trends in network-based intrusion detection systems (NIDS), their approaches, and the most common datasets used to evaluate IDS Models. The analysis presented in this paper is based on the number of citations acquired by an article published, the total count of articles published related to intrusion detection in a year, and most cited research articles related to the intrusion detection system in journals and conferences separately. Based on the published articles in the intrusion detection field for the last 15 years, this article also discusses the state-of-the-arts of NIDS, commonly used NIDS, citation-based analysis of benchmark datasets, and NIDS techniques used for intrusion detection. A citation and publication-based comparative analysis to quantify the popularity of various approaches are also presented in this paper. The study in this article may be helpful to the novices and researchers interested in evaluating research trends in NIDS and their related applications.

Introducing Machine Learning with Scratch and Robots as a Pilot Program for K-12 Computer Science Education

Machine learning (ML), a branch of artificial intelligence (AI), is a method that enables systems to learn from data for the purpose of recognizing patterns and making decisions without being explicitly programmed. In the past decade machine learning has been growing rapidly, and ML technologies such as speech recognition, spam filters, smart email reply, online recommendations, face recognition, fake news detection, and self-driving cars have become pivotal in modern daily life. However, computer science education has not yet fully adjusted to the tremendous growth in the sub-field of AI. This paper describes an approach of introducing K-12 students to ML through an on-line summer camp. The students are introduced to the concept of ML by hands-on activities of developing applications for recognizing text, numbers, sounds, images, and video data using a web-based cloud service tool "Machine Learning for Kids" and Scratch 3 programming language combined with Lego Mindstorms EV3 robots. The results show that the tools and technologies used in the camp are suitable for K-12 students, also when used in the form of online training. Pre and post surveys show that students express basic knowledge in ML and higher interest in coding and STEM after being exposed to the proposed training.

Efficient All-or-Nothing Public Key Encryption With Authenticated Equality Test

Public key encryption with equality test (PKEET for short) is a new cryptographic primitive which allows a proxy to check whether two ciphertexts encrypted under different public keys are of the same plaintext. PKEET has become a prospective candidate for various application scenarios, such as data management on encrypted databases, personal health record systems, spam filtering in encrypted email systems. In this paper, we propose an efficient all-or-nothing public key encryption scheme with authenticated equality test (AoN-PKEAET for short). In comparison with the existing PKEET schemes, the proposed scheme provides a new feature of ciphertext authentication before the plaintext equality test. It ensures that no misjudgement occurs when testing the equality between ciphertexts. Specially, the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathsf {Test}$ </tex-math></inline-formula> algorithm in the proposed scheme first authenticates the compared ciphertexts and the equality test is fulfilled only if the ciphertexts are authenticated as valid. With this new feature, the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathsf {Test}$ </tex-math></inline-formula> algorithm cannot output 0 (which means that the encrypted messages are different) when the two input ciphertexts are of an identical message, or it cannot output 1 (which means that the encrypted messages are identical) when the two input ciphertexts are of different messages. Under a redefined security model for AoN-PKEAET, we give the detailed security proof of the proposed scheme.

Intellectual property issues in artificial intelligence: specific reference to the service sector

Artificial intelligence (AI) has transformed almost every field of the service sector, such as finance, healthcare logistics, automotive and aviation. The innovative technologies can identify uneven patterns like spam filtering or payment deceit, and make aware businesses in actual time about questionable activities, hence are helpful in the growth of a market. These innovation and creation are protected under different forms of intellectual property (IP). However, the transformation from AI related inventions to AI lead inventions has raised substantial challenges to the existing IP infrastructure. This study aims at looking into different aspects of AI related IP protection with an elaborative analysis of the patenting trends through landscape analysis of AI in the service sector. It is observed that AI is playing a pivotal role in the transformation of the service sector due to its accelerating use. But the issues related to legal and ethical need to be addressed for effective utilisation of AI related invention and creation in the service sector.

Evading obscure communication from spam emails.

Spam is any form of annoying and unsought digital communication sent in bulk and may contain offensive content feasting viruses and cyber-attacks. The voluminous increase in spam has necessitated developing more reliable and vigorous artificial intelligence-based anti-spam filters. Besides text, an email sometimes contains multimedia content such as audio, video, and images. However, text-centric email spam filtering employing text classification techniques remains today's preferred choice. In this paper, we show that text pre-processing techniques nullify the detection of malicious contents in an obscure communication framework. We use Spamassassin corpus with and without text pre-processing and examined it using machine learning (ML) and deep learning (DL) algorithms to classify these as ham or spam emails. The proposed DL-based approach consistently outperforms ML models. In the first stage, using pre-processing techniques, the long-short-term memory (LSTM) model achieves the highest results of 93.46% precision, 96.81% recall, and 95% F1-score. In the second stage, without using pre-processing techniques, LSTM achieves the best results of 95.26% precision, 97.18% recall, and 96% F1-score. Results show the supremacy of DL algorithms over the standard ones in filtering spam. However, the effects are unsatisfactory for detecting encrypted communication for both forms of ML algorithms.

A Novel Approach to Control Emails Notification using NLP

The Digital era made Emails the omnipresent medium of information exchange and communication. One has to deal with a huge number of emails per day on a professional as well as personal level. This increases the chance of overlooking important and relevant emails. In this paper, we propose a novel approach to control Emails Notifications using NLP. Its objective is to notify only the top “n” number of prioritized emails by using Natural Language Processing Technique. The entire work has been carried in three phases: “the Spam Filtering and Clustering of emails”, “Similarity detection of new mail and allotment of emails to Clusters for notification” and “Cluster wise Ranking and Prediction of which email to notify”. Also, a simple “Similarity Detection algorithm” is proposed using the important words from the subject of the email.

Adaptive spam filtering system using complement Naïve Bayes model

Adaptive spam filtering system using complement Naïve Bayes model

Analysis of Naıve Bayes Algorithm for Email Spam Filtering

The upsurge in the volume of unwanted emails called spam has created an intense need for the development of more dependable and robust antispam filters. Machine learning methods of recent are being used to successfully detect and filter spam emails. We present a systematic review of some of the popular machine learning based email spam filtering approaches. Our review covers survey of the important concepts, attempts, efficiency, and the research trend in spam filtering. The preliminary discussion in the study background examines the applications of machine learning techniques to the email spam filtering process of the leading internet service providers (ISPs) like Gmail, Yahoo and Outlook emails spam filters. 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. Our review compares the strengths and drawbacks of existing machine learning approaches and the open research problems in spam filtering. We recommended deep learning and deep adversarial learning as the future techniques that can effectively handle the menace of spam emails

A Content Filtering from Spam Posts on Social Media using Weighted Multimodal Approach

The system for filtering spam posts on social media is preferred to obtain the relevant content and expected by users. The previous works on spam detection have been done to filter irrelevant content on email and social media based on text or image separately. Due to the social media posts are commonly in the form of image, text, or both, the multimodal data is preferred to improve the capability of system in handling filtering content on social media. In addition, a spam post containing multimodal data sometimes does not indicate spam in both data but only one. To improve the performance of system, we propose a weighted multimodal approach for filtering content from spam posts in social media using Convolutional Neural Network (CNN). The mechanism of weighted multimodal is by weighting of spam prediction results from image and text data. We also investigate the performance of CNN architectures for spam post detection that are 3-layer, 5-layer, AlexNet and VGG16. The performance of each architectures is evaluated by 8000 Indonesian posts in the form of image and text taken from Instagram posts. The results show that the highest accuracy achieves 0.9850 based on the combination of image and text by using a 5-layer architecture. The average accuracy of all CNN architectures using multimodal data is higher than only using image and text data separately.

Spam filtering based on PV-DBOW model

Spam filtering based on PV-DBOW model

Spam filtering based on PV-DBOW model

Spam filtering based on PV-DBOW model

Performance Evaluation of Email Spam Text Classification Using Deep Neural Networks

Spam in email box is received because of advertising, collecting personal information, or to indulge malware through websites or scripts. Most often, spammers send junk mail with an intention of committing email fraud. Today spam mail accounts for 45% of all email and hence there is an ever-increasing need to build efficient spam filters to identify and block spam mail. However, notably today’s spam filters in use are built using traditional approaches such as statistical and content-based techniques. These techniques don’t improve their performance while handling huge data and they need a lot of domain expertise, human intervention and they neglect the relation between the words in context and consider the occurrence of the word. To address these limitations, we developed a spam filter using deep neural networks. In this work, various deep neural networks such as RNN, LSTM, GRU, Bidirectional RNN, Bidirectional LSTM, and Bidirectional GRU are used to a built spam filter. The experimentation was carried out on two datasets, one is a 20 newsgroup dataset, which contains multi-classes with 20,000 documents and the other is ENRON, a dataset contains 5,000 emails. The custom-designed models have performed well on both benchmark datasets and attained greater accuracy.

Naïve Bayes Filter for Communication &amp; Enhancing Semantic in Email

Due tothe current pandemic of COVID-19, the world has turned into ONLINE modeand an increase in online communication thereby information exchange, sharing useful data through emails and other social Medias. So addressing the security issues places a vital role in computer security and shouldhave thepriorities. We need a security check to enhance the inbox so that the important information or emails should not reach to the spam box. In this paper to improve the filtering techniques, wehave adopted the Naïve Bayes approach in implementation and enhancing the spam filter in the email. Bayes’s approach is efficient, accurate, and simple in implementing the proposed algorithm. Bayes algorithm is used to verify correct semantic information of the email and avoidsthe pass to pass approach if the incoming mail is important. The Python language is used to develop the proposed algorithm.

Spam detection and high-quality features to analyse question –answer pairs

Purpose In community question and answer (CQA) services, because of user subjectivity and the limits of knowledge, the distribution of answer quality can vary drastically – from highly related to irrelevant or even spam answers. Previous studies of CQA portals have faced two important issues: answer quality analysis and spam answer filtering. Therefore, the purposes of this study are to filter spam answers in advance using two-phase identification methods and then automatically classify the different types of question and answer (QA) pairs by deep learning. Finally, this study proposes a comprehensive study of answer quality prediction for different types of QA pairs. Design/methodology/approach This study proposes an integrated model with a two-phase identification method that filters spam answers in advance and uses a deep learning method [recurrent convolutional neural network (R-CNN)] to automatically classify various types of questions. Logistic regression (LR) is further applied to examine which answer quality features significantly indicate high-quality answers to different types of questions. Findings There are four prominent findings. (1) This study confirms that conducting spam filtering before an answer quality analysis can reduce the proportion of high-quality answers that are misjudged as spam answers. (2) The experimental results show that answer quality is better when question types are included. (3) The analysis results for different classifiers show that the R-CNN achieves the best macro-F1 scores (74.8%) in the question type classification module. (4) Finally, the experimental results by LR show that author ranking, answer length and common words could significantly impact answer quality for different types of questions. Originality/value The proposed system is simultaneously able to detect spam answers and provide users with quick and efficient retrieval mechanisms for high-quality answers to different types of questions in CQA. Moreover, this study further validates that crucial features exist among the different types of questions that can impact answer quality. Overall, an identification system automatically summarises high-quality answers for each different type of questions from the pool of messy answers in CQA, which can be very useful in helping users make decisions.

Effective spam filter based on a hybrid method of header checking and content parsing

In recent years, hazardous e-mails arose, such as the e-mails infected with ‘viruses’ or ‘worms’ spreading destructive programs and the ‘Phishing Mails’ defrauding e-mail accounts of the users. The number of spams continue to grow. With the related problems of spam coming to be more severe, the spam topics have become significant in various research domains. The common filtering methods include black/white list, rule learning, and those based on text classification, such as Naive Bayes, support vector machine, and boosting trees, multi-agent and genetic algorithm. Among these, the methods based on text classification are most widely applied. Moreover, some efficient methods were proposed to consider only the e-mail's header section, based on which both operating efficiency and classification efficiency could be improved. By applying machine learning technique and decision tree data mining algorithm C4.5, this study aims to propose an efficient spam filtering method with the following features: (i) proposing a two-phase filtering mechanism to scan mainly e-mail's header and auxiliary content. (ii) Reducing the problem of false positive. The experimental results show that the authors’ method has a considerably high accuracy rate of 98.76%. Compared with some other methods of using the same spam data sets or of deep learning-based, their method obviously has an excellent performance.

AI-RADS: An Artificial Intelligence Curriculum for Residents

Rationale and ObjectivesArtificial intelligence (AI) has rapidly emerged as a field poised to affect nearly every aspect of medicine, especially radiology. A PubMed search for the terms “artificial intelligence radiology” demonstrates an exponential increase in publications on this topic in recent years. Despite these impending changes, medical education designed for future radiologists have only recently begun. We present our institution's efforts to address this problem as a model for a successful introductory curriculum into artificial intelligence in radiology titled AI-RADS.Materials and MethodsThe course was based on a sequence of foundational algorithms in AI; these algorithms were presented as logical extensions of each other and were introduced as familiar examples (spam filters, movie recommendations, etc.). Since most trainees enter residency without computational backgrounds, secondary lessons, such as pixel mathematics, were integrated in this progression. Didactic sessions were reinforced with a concurrent journal club highlighting the algorithm discussed in the previous lecture. To circumvent often intimidating technical descriptions, study guides for these papers were produced. Questionnaires were administered before and after each lecture to assess confidence in the material. Surveys were also submitted at each journal club assessing learner preparedness and appropriateness of the article.ResultsThe course received a 9.8/10 rating from residents for overall satisfaction. With the exception of the final lecture, there were significant increases in learner confidence in reading journal articles on AI after each lecture. Residents demonstrated significant increases in perceived understanding of foundational concepts in artificial intelligence across all mastery questions for every lecture.ConclusionThe success of our institution's pilot AI-RADS course demonstrates a workable model of including AI in resident education.