Email Spam Filter

Email deliverability is a critical factor in digital communication, determining whether messages reach recipients’ primary inboxes or are relegated to spam and promotional folders. This paper examines deliverability in the context of both traditional email marketing platforms and the emerging category of newsletter mailing platforms, including Substack, beehiiv, and LetterBucket. Drawing on industry studies, technical best practices, and user-reported outcomes, the analysis highlights how newsletter platforms achieve superior inbox placement. Their advantages stem from simplified content formats, engaged subscriber bases, consistent sending practices, and robust platform-level reputation management. Traditional marketing platforms maintain strong deliverability infrastructure but often face challenges due to promotional content classification.

When email became more widely used, in the late 1990s, I heard the term “snail mail” to refer to mail by post. Whereas anyone online could almost instantly send a little letter to someone else online, or a big one, if one uses traditional post it takes at least 12 hours to arrive, if not longer. But is email always faster than post, when it is logically and naturally possible than it can be? (There is no logical inconsistency and there is no violation of a law of nature: a miracle is not required.)



Imagine that one finds that for some items, the post takes a mysteriously long time to arrive. I found this when ordering old copies of psychoanalytic journals, one of which wrote of “conceptual scheme bs.” One concludes that there is some reason for this delay, and even constructs an economic model in which it is rational for post to arrive slowly in this case: slower than logically and naturally possible. But will not email now or soon be affected by the same model? After all, who provides us with email? Organizations, which must take into account economic good sense as well. Email might work instantly for you, but if you seek the kind of information I sought when ordering these journals, then you may well face the same problem.



But why  does email arrive slowly in these case? I am not always sure. Even if one does not construct an economic model at all for snail mail, if one assumes that there is economic reason with some of the delays, then one has reason to assume that these will occur with email as well.

The various forms and tremendous number of spam emails have brought great challenges to accurate email classification. In this paper, we present a behavior- and time-feature-based email classification method. Based on email logs, email social networks are built through the extraction of entities and relations from the email records using the MapReduce model. By combining behavior features from social networks and time features from email sending intervals, we adopt a Support Vector Machine based classifier to identify spammers and nonspammers. Compared with the current email classification methods, the advantages of our method are: (1) in addition to the behavior-based features, our method integrates the time feature to facilitate email classification; (2) to efficiently handle the vast number of emails, we employ the MapReduce model to extract the behavior- and time-based features on the email social network. Experiments on real email data of three years show that the proposed meth...

A phishing email is an attack that focused completely on people to circumvent existing traditional security algorithms. The email appears to be a dependable, appropriate, and solid communication medium for internet users. At present, the email is submerged with spam content, both in text-based form or undesired text planted inside the images. This study reviews articles on phishing image spam classification published from 2006 to 2020 based on spam classification application domains, datasets, features sets, spam classification methods, and the measurement metrics adopted in the existing studies. More than 50 articles, both from Web of Science and Scopus databases were picked. Achieving the study's target, we carried out a broad survey and analysis to identify the domains where spam classification was applied. Furthermore, several public data sets, features set, classification methods, and measuring metrics are found and the popular once were pinpointed. The study revealed that Personal Collection, Dredze, and Spam Archives datasets are the most commonly used datasets in image spam classification research. Low-level and image metadata are the most widely used features set. The methods of image spam classification as identified in this study are supervised machine learning, unsupervised machine learning, semi-supervised machine learning, content-based and statistical learning. Among these methods, the most commonly utilized is the Support Vector Machine (SVM) which falls under supervised machine learning. This is followed by Naïve Bayes and K-Nearest Neighbor. The commonly adopted metrics for the performance evaluation of the existing image spam classifiers are also identified and briefly discussed. We compared the performance of the state-of-the-art image spam models. Lastly, we pointed out promising directions for future research.

The exponential growth of mobile communication has intensified the threat of SMS spam, compromising user security and trust in messaging platforms. This study addresses this challenge by designing and deploying a robust spam detection system using machine learning. We analyze a publicly available SMS dataset through rigorous pre-processing, including text normalization, tokenization, and feature engineering, followed by TF-IDF vectorization. A comparative evaluation of 11 classifiers-spanning probabilistic models, ensemble methods, and linear classifiers-reveals that ensemble techniques outperform traditional algorithms. The Extra Trees Classifier and XGBoost achieve state-of-the-art results, with 97.9% accuracy and 97.5% precision, demonstrating their efficacy in distinguishing spam from legitimate messages. To bridge the gap between research and practical application, we develop an interactive Streamlit web application that enables real-time spam classification with a user-friendly interface. This work underscores the potential of ensemble learning for text classification tasks and provides a scalable framework for combating SMS spam in real-world scenarios.

In this paper, the clustering Algorithm known as Support Vector Classifier (SVC) is used. SVC offers classifiers such as logistic regression and decision trees that provide very high accuracy compared to others. The model first preprocesses the input after that extracts the required details then it classifies the details and finally detection. SVC presents a workload that is data intensive and compute. To reduce the workload the model trained offline, achieving 97.95% top-1 accuracy. And it also segmentation and preprocessing is also used to minimize input image size fed into SVM.

Spam consists of varieties of contents like text, image, embedded HTML, MIME attachments and also the volume of spam mails sent per day is massive. To handle this high volume, high velocity and large varieties of spam, a scalable spam filtering solution is required. Scalable solutions available for machine learning and statistical studies can be used to implement a scalable solution for spam filtering also. From Big data Analytics domain, Mahout is an open source library from Apache for building scalable solutions in machine learning. This paper uses mahout framework to analyse the time and accuracy efficiencies of the results of two Naive Bayes classification algorithms. Keywords: Apache Mahout, big data, scalable algorithms, Naive Bayes algorithms

this research project acts as a foundational guide for students and early-career professionals interested in AI. It combines academic theory, technical practice, and ethical reflection to provide a holistic understanding of AI and machine learning.

This paper presents a framework to detect spammers and fake users on social networking platforms using machine learning algorithms. With the rise in usage of platforms like Twitter and Facebook, malicious activities like spam posting and creation of fake accounts have significantly increased. Our proposed model uses machine learning algorithms like CatBoost, AdaBoost, and LSTM to classify and identify fake accounts. The system architecture, methodology, and results demonstrate effective detection with improved accuracy and reduced complexity, contributing to safer digital social environments.

The widespread use of email as a primary communication medium has led to an increase in spam messages, which pose significant threats to privacy, productivity, and cybersecurity. Spam emails, often disguised as legitimate messages, can carry malicious links, phishing scams, and fraudulent content. This paper presents a machine learning-based approach for identifying spam emails with high accuracy. By employing natural language processing (NLP) techniques and the Naïve Bayes classifier, we preprocess a labeled dataset of email messages, extract relevant features, and train a classification model. The model's effectiveness is evaluated using performance metrics such as accuracy, precision, recall, and F1-score. The results demonstrate the reliability and practicality of machine learning in mitigating email spam, offering a scalable and adaptive solution to an ongoing digital challenge

The number of email users is increasing every day worldwide. If you have to communicate officially with someone, whether in a business matter or with someone else, your electronic mail is the best option. When identifying the emails, 52-60% were spam. Spammers use such creative methods that it is difficult to determine whether the email is spam. This study focused on classifying spam emails for detection with high accuracy using a machine-learning algorithm. This research involved using multiple datasets and applying various algorithms, such as Random Forest, Logistic Regression, Naïve Bayes, and SVM, to determine how they perform. Additionally, other approaches, such as Feature Engineering, Bagging, and Boosting, have been utilized. The implementation of feature engineering techniques is aimed at enhancing the performance and accuracy of the model. The effectiveness of the framework focuses on metrics such as accuracy, precision, recall, and F1-score. These findings are expected to contribute to improved spam detection mechanisms. This research not only addresses current limitations in spam detection but also sets the stage for future advancements in the field. The findings will contribute to reducing the risk of spam filters and malicious emails and enhance cyber security.

The advanced architecture of Large Language Models (LLMs) has revolutionised natural language processing, enabling the creation of text that convincingly mimics legitimate human communication, including phishing emails. As AI-generated phishing emails become increasingly sophisticated, a critical question arises: How effectively can current email systems and detection mechanisms identify these threats? This study addresses this issue by analysing 63 AI-generated phishing emails created using GPT-4o. It evaluates the effectiveness of major email services, Gmail, Outlook, and Yahoo, in filtering these malicious communications. The findings reveal that Gmail and Outlook allowed more AI-generated phishing emails to bypass their filters compared to Yahoo, highlighting vulnerabilities in existing email filtering systems. To mitigate these challenges, we applied 60 stylometric features across four machine learning models: Logistic Regression, Support Vector Machine, Random Forest, and XGBoost. Among these, XGBoost demonstrated superior performance, achieving 96% accuracy and an AUC score of 99%. Key features such as imperative verb count, clause density, and firstperson pronoun usage were instrumental to the model's success. The dataset of AI-generated phishing emails is publicly available on Kaggle to foster further research.

During the past thirty years, the world of computing has evolved from large centralised computing centres to an increasingly distributed computing environment, where computation and communication capabilities are being embedded in artefacts of everyday life. Billions of computational entities will interact in systems with ever changing configurations determined by local and global context, for example, the location of the user. In such dynamic environments, users would be overwhelmed if involved in computing-related decisions every time the context changes. Due to the number of decisions required to sustain continuous service, most decisions will have to be made by the computing entities themselves. Moreover, due to the global scale of the environment and the potential risk of disconnected operations, the computing entities may have to make these decisions autonomously, without relying on a given fixed infrastructure. Knowledge, especially about the context of the interaction, is vital for the accuracy of these decisions. However, keeping information on a global scale is unfeasible for resource-constrained entities, so some degree of uncertainty must be assumed. This peer-to-peer type of interaction in an uncertain world where interactions are needed to go forward resembles what occurs in human social networks. The notion of trust has emerged in human society to allow humans to make decisions under such circumstances. It has been proposed that computing entities can make decisions based on a computational model of trust. The trust engine run by each entity distributes and gathers pieces of evidence, that is, knowledge about the interacting entities: direct observations, recommendations or reputation. Since the trust engines collaborate and malicious collaborating entities exist, security through collaboration must be considered. As the real world does not have a unique legitimate authority, computing entities are owned by multiple authorities and operated from multiple jurisdictions. As in real life, no administrator can be perpetually present to manage the interactions. The trust engine can adapt security in a peer-to-peer way. A crucial element for the use of trust is to know with whom the entities interact, which corresponds to authentication in traditional computer security. However, this element has been disregarded in computational trust: this is ill-fated given that virtual identities are the means for a number of attacks that are less possible in face-to-face settings. This thesis sets up a framework, called entification, which encompasses both computational trust and identity aspects, and whose goal is to be applicable to global computing. For this purpose, this thesis

With the rise of Social Media platforms and new applications, the Rapid Expansion of fake accounts has become an important concern, posing threats to security, privacy and trustworthiness. In response, this research explores the application of machine learning techniques for the detection and reduction of fake accounts. By utilizing datasets containing, user behavior patterns, network characteristics and various parameters, we explore the efficiency of various machine learning algorithms in selective genuine users from false ones. This study includes attribute manipulation, model training and evaluation techniques made for the unique challenges of fake account detection. We examine the effects of different features, such as interaction measures, language patterns and network structures on the output of detection models. Through systematic testing and validation, we identify effective methods for accurately identifying fake accounts in broad virtual spaces. Our results to the progress of information security efforts and the improvement of user trust in online platforms.

The internet has made it easier than ever to connect and do business. But it's also given bad guys more ways to trick people. Phishing is a common online scam where criminals try to get your personal information, like passwords and bank details. They often pretend to be someone you trust-maybe your bank, a popular online store, or even a friend. They might send you an email that looks official, with logos and convincing language, asking you to click a link or open an attachment. This link often takes you to a fake website that looks just like the real thing, where they try to steal your login information.

With the continuous rise in the number of mobile device users, SMS (Short Message Service) remains a prevalent communication tool accessible on both smartphones and basic phones. Consequently, SMS traffic has experienced a significant surge. This increase has also led to a rise in spam messages, as spammers seek financial or business gains through activities like marketing promotions, lottery scams, and credit card information theft. Consequently, spam classification has become a focal point of research. In this paper, we explore the effectiveness of 11 machine learning algorithms for SMS spam detection, including multinomial Naïve Bayes, K-Nearest Neighbors (KNN), and Random Forest, among others. Utilizing datasets from UCI and Bangla SMS collections, our experimental results reveal that the multinomial Naïve Bayes algorithm surpasses previous models in spam detection, achieving accuracies of 98.65% and 89.10% in the respective datasets.

Combatting email spam has remained a very daunting task. Despite the over 99% accuracy in most non-image-based spam email detection, studies on image-based spam hardly attain such a high level of accuracy as new email spamming techniques that defeat existing spam filters emerges from time to time. The number of email spams sent out daily has remained a key factor in the continued use of spam. In this paper, a simple convolutional neural network model, 123DNet was developed and trained with 28,929 images drawn from 2 public datasets and a Personally Generated dataset. The model was optimized to the least set of layers to have 1 input layer, 2 embedded Convolutional layers as a hidden layer, and 3 neural network layers. The model was tested with a total of 4,339 images of the three dataset samples and then with a separate set of 1,200 images to test performance on never-seen-before images. A Classification Performance analysis was carried out using the confusion matrix. Performance metrics including Accuracy, Precision, True Negative Accuracy, Sensitivity, Specificity, and F1 Measure were computed to ascertain the model's performance. The Model returned an F1 Score of 97% on a public dataset's test sample and 88% on Never-seen-before test samples outperforming some pre-existing models while performing significantly well on the newly generated image test samples. It is recommended that a model that performed so well with new never-seen-before spam images be integrated into spam filtering systems.

Phishing is still one of the biggest threats in cybersecurity. It is the exploitation of users through the use of deceptive URLs. In this study, the outcomes of the Random Forest, Support Vector Machines, and Decision Tree models are analysed on a dataset containing more than 640,000 URLs. The results showed that Random Forest recorded the highest accuracy of 87.85% on the Aalto dataset and 86.86% on the Kaggle dataset. These perspectives provide a more fact-based approach towards developing more effective and practical anti-phishing systems.

Email spam is a kind of electronic spam, which tends to be a more difficult problem nowadays among all internet challenges. Spam mails are mostly sent in commercial purpose, some of them may contain malware links that lead to phishing websites. The aim of this study is to classify into ham and spam emails with an optimized and well efficient classification technique. Ham holds emails that are legitimate or legally valid message can get accepted by users. Spam emails are unwanted emails that a user doesn't want and to get rid of it. This study emphasizes on the improvement in classifying all mails into these two groups with minimal requirement of training and with an accuracy of hundred percent. Here in this study, Modified Naïve Bayes (MNB) classifier ensured the requirements with very low percentage of training and produces accurate results than existing Naïve Bayes (NB) or Supporting Vector Machine (SVM) classifier.

The series "Lecture Notes in Networks and Systems" publishes the latest developments in Networks and Systems-quickly, informally and with high quality. Original research reported in proceedings and post-proceedings represents the core of LNNS. Volumes published in LNNS embrace all aspects and subfields of, as well as new challenges in, Networks and Systems. The series contains proceedings and edited volumes in systems and networks, spanning the areas of Cyber

The use of email has grown exponentially over the past decade, making it one of the most widely used forms of electronic communication. Recently, spam emails have become a major issue for email users. A spammer is someone who sends out unsolicited, mass emails. It causes problems for email servers, wastes time, and uses up bandwidth. There are a variety of spam filtering techniques that can be used to divide incoming email into spam and legitimate communications. The average user is negatively impacted due of the proliferation of spam emails, which makes it more difficult to find the truly useful messages and can even drive some to ignore crucial ones. Therefore, there is a requirement for an efficient email spam detector that can block the maximum number of spam emails with the highest degree of precision, ensuring that no legitimate emails are mistakenly deleted as spam. This work proposes a hybrid strategy for detecting spam emails by using Modified Particle Swarm Optimization for Anti-Spam Filtering System (MPSO_ASFS). The data employed in this work is linearly separable, and the Proposed MGA ASFS approach achieved higher accuracy than competing classifiers on the Ling Spam Corpus dataset (92.23%), the PU dataset (94.56%), the Enron Corpus dataset (91.34%), and the Spam Assassin dataset (91.35%).

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 leaning and deep adversarial learning as the future techniques that can effectively handle the menace of spam emails.

The rapid development of email use and the convenience provided make email as the most frequently used means of communication. Along with its development, many parties are abusing the use of email as a means of advertising promotion, phishing and sending other unimportant emails. This information is called spam email. One of the efforts in overcoming the problem of spam emails is by filtering techniques based on the content of the email. In the first study related to the classification of spam emails, the Naïve Bayes method is the most commonly used method. Therefore, in this study researchers will add Random Forest and K-Nearest Neighbor (KNN) methods to make comparisons in order to find which methods have better accuracy in classifying spam emails. Based on the results of the trial, the application of Naïve bayes classification algorithm in the classification of spam emails resulted in accuracy of 83.5%, Random Forest 83.5% and KNN 82.75%.

In the real world, many online shopping websites or service provider have single email-id where customers can send their query, concern etc. At the back-end service provider receive million of emails every week, how they can identify which email is belonged of a particular department? This paper presents an artificial neural network (ANN) model that is used to solve this problem and experiments are carried out on user personal Gmail emails datasets. This problem can be generalised as typical Text Classification or Categorization [8].

With the advent of the internet, along with email, and social networking, there are some new issues that have caused vulnerability of users against attackers. Internet users face a lot of undesirable emails and their data privacy and security is in danger. Spammers are often sent to users by intruders and sales markets, and most of the time they target spam, harassment, and abuse of user data. With increasing attacks on computer networks, attempts to rebuild computer networks and detect spam emails are important. Hackers use the identities of users by obtaining their personal information and account of users for malicious and subversive actions. Intruders are attempting to expose, remove, or change user information by opening encrypted information. Therefore, it is very important to detect spam in the early stages. In this paper, a new approach is proposed based on a hybridization of Particle Swarm Optimization (PSO) with Fruit Fly Optimization (FFO) to email spam detection. This paper shows a Feature Selection (FS) based on PSO, which decreases dimensionality and improves the accuracy of email spam classification. The PSO searches the feature space for the best feature subsets. Experiments results on the public spambase dataset show that the accuracy of the proposed model is 92.21%, which is better in comparison with others models, such as PSO, Genetic Algorithm (GA), and Ant Colony Optimization (ACO).

Social media and e-commerce platforms have led online communities to utilize reviews as a means of exchanging opinions about products, services, and issues. Reviews can also help customers make better purchasing decisions by analyzing customer feedback, and they can help businesses improve the quality of their manufacture. However, the spread of fake reviews misleads individuals, which is a concerning issue. Online consumers either enhance or diminish the standing of rival brands. This paper suggests a strategy for detecting fake reviews of online textual content through assisted learning. The technique uses honest reviews and machine learning classifiers to split off fake data. Planned system performance is compared to the baseline, and experimental results are compared to assessment metrics.

Social media and e-commerce sites have prompted online communities to use reviews to provide input on goods, products, and services, as well as to support people to analyze customer input for buying choices, and corporations to improve manufacturing quality. Internet shoppers support or degrade the reputation of competitive brands. However, the dissemination of fake reviews fools people, making these reviews a worrying problem. This study proposes a guided learning online textual content fraudulent review detecting method. The work splits bogus data using machine learning classifiers and honest reviews. Experimental findings are compared to assessment measures. Planned system performance is compared to the baseline. The research comes to the conclusion that supervised machine learning techniques may be useful in identifying fraudulent reviews, but how well these techniques work is largely reliant on the characteristics that are chosen. In terms of accuracy, AUC, and other performance metrics, the SVM classifier with N-Gram feature extraction and CV feature selection performs better than other classifiers and feature selection techniques. This is shown by the examination of various feature extraction and selection techniques. According to the research, N-Gram feature extraction and CV feature selection may be helpful in spotting fraudulent reviews on e-commerce platforms. This would assist customers in making wise selections and increase the reliability of online reviews.

Feature extraction plays an important role in accurate preprocessing and real-world applications. High-dimensional features in the data have a significant impact on the machine learning classification system. Relevant feature extraction is a fundamental step not only to reduce the dimensionality but also to improve the performance of the classifier. In this paper, the author proposes a hybrid dimensionality reduction technique using principal component analysis (PCA) and singular value decomposition (SVD) in a machine classification system with a support vector classifier (SVC). To evaluate the performance of PCSVD, the results are compared without using feature extraction techniques or with existing methods of independent component analysis (ICA), PCA, linear discriminant analysis (LDA), and SVD. In addition, the efficiency of the PCSVD method is measured on an increased scale of 1.54% accuracy, 2.70% sensitivity, 3.71% specificity, and 3.58% precision. In addition, reduce the 15% ...

Here we present an inclusive review of recent and successful content-based e-mail spam filtering techniques. Our focus is primarily on machine learning-based spam filters and variants that are inspired by them. We report on related ideas, techniques, major efforts and cutting-edge art in the field. Preliminary interpretation of prior work shows the basics of e-mail spam filtering and feature engineering. In this we conclude by studying techniques, methods, evaluation criteria, and explore promising apprehensions of the latest developments and suggest future lines of investigation.

The Spamming is the use of messaging systems to send multiple unsolicited messages (spam) to large numbers of recipients for the purpose of commercial advertising, for the purpose of non-commercial proselytizing, for any prohibited purpose, or simply repeatedly sending the same message to the same user. Internet of Things (IoT) enables convergence and implementations between the real-world objects irrespective of their geographical locations. Implementation of IOT network management and control makes privacy and protection strategies utmost important and challenging in such an environment. This dissertation presents an adaptive approach based on deep learning for detecting of spam in the IOT network. The CNN-LSTM techniques is applied and optimized for better performance than others. For each topic, the existing problems are analyzed, and then, current solutions to these problems are presented and discussed. The simulation results show that the proposed sentiment analysis method has higher precision, recall and F1 score. The method is proved to be effective with high accuracy. The simulation and analysis are done using the python spider 3.7 software. The overall accuracy achieved by the proposed work is 94.25 % while previous it is achieved 92.8 %. The error rate of proposed technique is 4.37 % while 8.2 % in existing work. Therefore, it is clear from the simulation results; the proposed work is achieved significant better results than existing work.

Spam emails are one of the crucial problems faced by most of the email users. There are a lot of algorithms to filter spam mails from ham mails. In this paper two efficient filters-Bayesian filters and Artificial Immunity filters are studied and compared. Bayesian classifier has been suggested as an effective method to construct anti-spam filters for its strong categorization and high precision. Artificial immune system has become a new embranchment in computing intelligence for its good selflearning, self-adaptability and robustness. This paper proposes a new hybrid filtering system based on Bayesian, AIS and the concept of blacklist and whitelist .

E-mail is an efficient and reliable data exchange service. Spams are undesired email messages which are randomly sent in bulk usually for commercial aims. Obfuscated image spamming is one of the new tricks to bypass text-based and Optical Character Recognition (OCR)-based spam filters. Image spam detection based on image visual features has the advantage of efficiency in terms of reducing the computational cost and improving the performance. In this paper, an image spam detection schema is presented. Suitable image processing techniques were used to capture the image features that can differentiate spam images from non-spam ones. Weighted k-nearest neighbor, which is a simple, yet powerful, machine learning algorithm, was used as a classifier. The results confirm the effectiveness of the proposed schema as it is evaluated over two datasets. The first dataset is a real and benchmark dataset while the other is a real-like, modern, and more challenging dataset collected from social media and many public available image spam datasets. The obtained accuracy was 99.36% and 91% on benchmark and the proposed dataset, respectively.

At present, spam is an actual and increasing problem that compromises email communications across the world. Thus, several solutions have been proposed to stop or reduce the amount of this threat. However, methods based on negative selection algorithm (NSA) lack continuous adaptability and suffer from low detection performance. Moreover, these methods require a large number of detectors to cover all non-self spaces. Thus, this study proposes a new e-mail detection approach based on an improved NSA called combined clustered NSA and fruit fly optimization (CNSA-FFO). The system combines actual NSA with k-means clustering and FFO to enhance the efficiency of classic NSA. Experiments results in spam benchmark show that the performance of CNSA-FFO is better than the classic NSA and NSA-PSO, especially in terms of detection accuracy, positive prediction, and computational complexity.

Hybrid spam is an undesirable e-mail (electronic mail) that contains both image and text parts. It is more harmful and complex as compared to image-based and text-based spam e-mail. Thus, an efficient and intelligent approach is required to distinguish between spam and ham. To our knowledge, a small number of studies have been aimed at detecting hybrid spam e-mails. Most of these multimodal architectures adopted the decision-level fusion method, whereby the classification scores of each modality were concatenated and fed to another classification model to make a final decision. Unfortunately, this method not only demands many learning steps, but it also loses correlation in mixed feature space. In this paper, we propose a deep multimodal feature-level fusion architecture that concatenates two embedding vectors to have a strong representation of e-mails and increase the performance of the classification. The paragraph vector distributed bag of words (PV-DBOW) and the convolutional ne...

The proliferation of spam emails, a predominant form of online harassment, has elevated the significance of email in daily life. As a consequence, a substantial portion of individuals remain vulnerable to fraudulent activities. Despite Gmail’s “spam mail filtration system,” its effectiveness is not absolute. It occasionally misclassifies legitimate messages, leading to their confinement in the spam folder, or overlooks potentially harmful spam emails. This results in the occurrence of false positives. This research scrutinizes the historical data, cookies, caches, Session Restores, flash artifacts, and super cookies of Internet Explorer, Firefox, and Chrome on the Windows 10 platform. Data was collected through Google, Firefox, and Internet Explorer, operating within the Windows 10 environment. It has been observed that browsers store user behavior data on the host computer’s hard drive. The implications of this study hold substantial value for computer forensics researchers, law en...

With the rapid increase in internet users, e-mail spam is also increasing, which has become a major problem. Now a days, emails have two subcategories: spam and ham. In addition to harming the system, malicious link senders via spam emails can also try to access your system. The creation of a phoney email account makes it much simpler for spammers to pose as real people and target unsuspecting individuals. It is required to identify the spam mail, which is a fraud. This paper will identify email spam by using various techniques of machine learning. In this paper, we will discuss how the machine learning algorithms are applied to our data sets "Ling Spam of spam assassin" and analyse the results, and the best algorithm among them will be chosen for the identification of email spam.

Recently, machine learning has been applied into different major areas such as text classi cation, machine translation, and spam detection. The great performance of machine learning algorithms into several elds provided the humans with opportunities to tackle some of their hard jobs to be handled by machine learning systems. These tasks seem effortless for machines, and need less time as the amount of texts or spams need to be classi ed is huge. Hence, in his paper, we propose three different models for the task of emails spam detection. The three models are trained and validated on a public spam dataset. Experimentally, the models performed differently and it was seen that the Naïve Bayes outperformed the other machine learning algorithms in terms of accuracy and other evaluation metrics.

Recently, machine learning has been applied into different major areas such as text classification, machine translation, and spam detection. The great performance of machine learning algorithms into several fields provided the humans with opportunities to tackle some of their hard jobs to be handled by machine learning systems. These tasks seem effortless for machines, and need less time as the amount of texts or spams need to be classified is huge. Hence, in his paper, we propose three different models for the task of emails spam detection. The three models are trained and validated on a public spam dataset. Experimentally, the models performed differently and it was seen that the Naïve Bayes outperformed the other machine learning algorithms in terms of accuracy and other evaluation metrics.

In contemporary email communication, the everexpanding volume of digital correspondence has ushered in an era where big data plays a pivotal role in addressing the challenge of distinguishing between legitimate (ham) and unsolicited (spam) emails. The primary objective of this paper is the meticulous identification and establishment of criteria for the discrimination between ham and spam emails. To achieve this, the study harnesses data from three distinct datasets, aiming to identify common attributes shared across all emails, irrespective of their classification, while concurrently devising methodologies for precise spam detection. Central to this endeavor is the evaluation of the effectiveness of feature selection techniques, specifically Chi-Square and Pearson Correlation, in elevating the accuracy of email classification. The investigation extends to assessing how the combination of these feature selection techniques with the broader machine learning framework can be optimized. This optimization entails the application of diverse preprocessing techniques to the datasets, all designed to amplify the precision of email classification. Furthermore, this research scrutinizes the performance evaluation metrics employed in the assessment of email classifiers. By conducting comprehensive experiments, the study identifies optimal classifiers based on rigorous evaluation metrics. This contributes valuable insights to the toolkit of techniques for proficient email classification within the realm of big data analysis.

The continuous growth of email users has resulted in the increasing of unsolicited emails also known as Spam. In current, server side and client side anti spam filters are introduced for detecting different features of spam emails. However, recently spammers introduced some effective tricks consisting of embedding spam contents into digital image, pdf and doc as attachment which can make ineffective to current techniques that is based on analysis digital text in the body and subject fields of email. Many of proposed working strategy provides an anti spam filtering approach that is based on data mining techniques which classify the spam and ham emails. The effectiveness of these approaches is evaluated on large corpus of simple text dataset as well as text embedded image dataset. But most of the filtering techniques are unable to handle frequent changing scenario of spam mails adopted by the spammers over the time. Therefore improved spam control algorithms or enhancing the efficiency of various existing data mining algorithms to its fullest extent are the utmost requirement. A comparative study is presented on various spam filtering techniques adopted on the basis of various attributes to find best among all to extract the best results.

Short Message Service (SMS) is one of the most frequently used services in the mobile phones, next to calls. In developing countries like India, SMS is the cheapest mode of communication. The advantage of this fact is exploited by the advertising companies to reach masses. The unsolicited SMS messages (a.k.a. spam SMS) generates notifications, thus consuming precious user attention. To formulate spam SMS problem and understand user's needs and preceptions, we conducted an online survey with 458 participants in different cities of India. Most of the survey participants admitted that they are quite annoyed with burst of SMS spams and ineffectiveness of regulatory solutions. However, some participants reported that, they do get useful information from spam SMSes sometime(e.g. discounts at a popular food joint). In this paper, we present design and implementation of a usercentric spam SMS filtering application i.e. SMSAssassin that uses content based machine learning techniques with user generated features to filter unwanted SMSes and reduces the burden of notifications for a mobile user.

Financial fraud detection poses a critical challenge in the contemporary digital economy due to its potential to inflict substantial harm on individuals, businesses, and financial institutions. In this research, we introduce an innovative approach that combines Genetic Programming (GP) with Convolutional Neural Network (CNN) optimization to enhance the accuracy and efficiency of financial fraud detection systems. Genetic programming is leveraged to evolve and optimize the architecture of the CNN model, tailoring it to the unique patterns and features inherent in financial transaction data. The primary objective of this proposed method is to autonomously discover and adapt the optimal CNN structure for fraud detection, thereby reducing the need for manual feature engineering and improving the model's capacity to generalize across various fraud scenarios. We conduct extensive experiments on realworld financial datasets, comparing the performance of our approach with traditional methods and standalone CNN models. The results underscore the efficacy of the proposed method, underscoring its potential to offer robust and adaptive solutions for financial fraud detection.

Short Message Service (SMS) is one of the most frequently used services in the mobile phones, next to calls. In developing countries like India, SMS is the cheapest mode of communication. The advantage of this fact is exploited by the advertising companies to reach masses. The unsolicited SMS messages (a.k.a. spam SMS) generates notifications, thus consuming precious user attention. To formulate spam SMS problem and understand user's needs and preceptions, we conducted an online survey with 458 participants in different cities of India. Most of the survey participants admitted that they are quite annoyed with burst of SMS spams and ineffectiveness of regulatory solutions. However, some participants reported that, they do get useful information from spam SMSes sometime(e.g. discounts at a popular food joint). In this paper, we present design and implementation of a usercentric spam SMS filtering application i.e. SMSAssassin that uses content based machine learning techniques with user generated features to filter unwanted SMSes and reduces the burden of notifications for a mobile user.

The internet has provided numerous modes for secure data transmission from one end station to another, and email is one of those. The reason behind its popular usage is its cost-effectiveness and facility for fast communication. In the meantime, many undesirable emails are generated in a bulk format for a monetary benefit called spam. Despite the fact that people have the ability to promptly recognize an email as spam, performing such task may waste time. To simplify the classification task of a computer in an automated way, a machine learning method is used. Due to limited availability of datasets for email spam, constrained data and the text written in an informal way are the most feasible issues that forced the current algorithms to fail to meet the expectations during classification. This paper proposed a novel, spam mail detection method based on the document labeling concept which classifies the new ones into ham or spam. Moreover, algorithms like Naive Bayes, Decision Tree and Random Forest (RF) are used in the classification process. Three datasets are used to evaluate how the proposed algorithm works. Experimental results illustrate that RF has higher accuracy when compared with other methods.

The internet has provided numerous modes for secure data transmission from one end station to another, and email is one of those. The reason behind its popular usage is its cost-effectiveness and facility for fast communication. In the meantime, many undesirable emails are generated in a bulk format for a monetary benefit called spam. Despite the fact that people have the ability to promptly recognize an email as spam, performing such task may waste time. To simplify the classification task of a computer in an automated way, a machine learning method is used. Due to limited availability of datasets for email spam, constrained data and the text written in an informal way are the most feasible issues that forced the current algorithms to fail to meet the expectations during classification. This paper proposed a novel, spam mail detection method based on the document labeling concept which classifies the new ones into ham or spam. Moreover, algorithms like Naive Bayes, Decision Tree and Random Forest (RF) are used in the classification process. Three datasets are used to evaluate how the proposed algorithm works. Experimental results illustrate that RF has higher accuracy when compared with other methods.

In the modern era, mobile phones have become ubiquitous, and Short Message Service (SMS) has grown to become a multi-million-dollar service due to the widespread adoption of mobile devices and the millions of people who use SMS daily. However, SMS spam has also become a pervasive problem that endangers users' privacy and security through phishing and fraud. Despite numerous spam filtering techniques, there is still a need for a more effective solution to address this problem [1]. This research addresses the pervasive issue of SMS spam, which poses threats to users' privacy and security. Despite existing spam filtering techniques, the high false-positive rate persists as a challenge. The study introduces a novel approach utilizing Natural Language Processing (NLP) and machine learning models, particularly BERT (Bidirectional Encoder Representations from Transformers), for SMS spam detection and classification. Data preprocessing techniques, such as stop word removal and tokenization, are applied, along with feature extraction using BERT. Machine learning models, including SVM, Logistic Regression, Naive Bayes, Gradient Boosting, and Random Forest, are integrated with BERT for differentiating spam from ham messages. Evaluation results

With the emergence of big data and the interest in deriving valuable insights from ever-growing and ever-changing streams of data, machine learning has appeared as an effective data analytic technique as compared to traditional methodologies. Big data has become a source of incredible business value for almost every industry. In this context, machine learning plays an indispensable role of providing smart data analysis capabilities for uncovering hidden patterns. These patterns are later translated into automating certain aspects of the decision-making processes using machine learning classifiers. This paper presents a state-of-the-art comparative analysis of machine learning and deep learning-based classifiers for multiclass prediction. The experimental setup consisted of 11 datasets derived from different domains, publicly available at the repositories of UCI and Kaggle. The classifiers include Naïve Bayes (NB), decision trees (DTs), random forest (RF), gradient boosted decision trees (GBDTs), and deep learning-based convolutional neural networks (CNN). The results prove that the ensemble-based GBDTs outperform other algorithms in terms of accuracy, precision, and recall. RF and CNN show nearly similar performance on most datasets and outperform the traditional NB and DTs. On the other hand, NB shows the lowest performance as compared to other algorithms. It is worth mentioning that DTs show the lowest precision score on the Titanic dataset. One of the main reasons is that DTs suffer from overfitting and use a greedy approach for attribute relationship analysis.