An Improved Spam Detection Method with Weighted Support Vector Machine

Vishagini, V; Rajan, Archana K

doi:10.1109/icdse.2018.8527737

Cited by 19 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e increase in the weight value can reduce the email misclassification. Experiments show that the performance of the spam detection system still needs to be improved in terms of precision and accuracy [14]. Karhika and Visalakshi described a method of spam classification implementing and combining and implementing the ant colony optimization and support vector machine methods.…”

Section: Rule-based Methodmentioning

confidence: 99%

Semantic Graph Neural Network: A Conversion from Spam Email Classification to Graph Classification

Pan

Gao

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

In this study, we propose a method named Semantic Graph Neural Network (SGNN) to address the challenging task of email classification. This method converts the email classification problem into a graph classification problem by projecting email into a graph and applying the SGNN model for classification. The email features are generated from the semantic graph; hence, there is no need of embedding the words into a numerical vector representation. The method performance is tested on the different public datasets. Experiments in the public dataset show that the presented method achieves high accuracy in the email classification test against a few public datasets. The performance is better than the state-of-the-art deep learning-based method in terms of spam classification.

show abstract

Section: Rule-based Methodmentioning

confidence: 99%

Semantic Graph Neural Network: A Conversion from Spam Email Classification to Graph Classification

Pan

Gao

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…1 summarizes the environment and data in which the methodology was tested; performance was evaluated in terms of accuracy (ACC), F1-score (F1), precision (P), and recall (R). Downloaded datasets and existing methods in the literature [24,[27][28][29][30][31][32][33][34][35][36] were used for performance evaluation assuming an anonymous attack through malicious email. As a result of classification, liked and separated corpus were distinguished.…”

Section: The Expression Is As Followsmentioning

confidence: 99%

AI-Enabled Grouping Bridgehead to Secure Penetration Topics of Metaverse

Park¹,

Siddiqui²,

Qureshi³

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

With the advent of the big data era, security issues in the context of artificial intelligence (AI) and data analysis are attracting research attention. In the metaverse, which will become a virtual asset in the future, users' communication, movement with characters, text elements, etc., are required to integrate the real and virtual. However, they can be exposed to threats. Particularly, various hacker threats exist. For example, users' assets are exposed through notices and mail alerts regularly sent to users by operators. In the future, hacker threats will increase mainly due to naturally anonymous texts. Therefore, it is necessary to use the natural language processing technology of artificial intelligence, especially term frequency-inverse document frequency, word2vec, gated recurrent unit, recurrent neural network, and long-short term memory. Additionally, several application versions are used. Currently, research on tasks and performance for algorithm application is underway. We propose a grouping algorithm that focuses on securing various bridgehead strategies to secure topics for security and safety within the metaverse. The algorithm comprises three modules: extracting topics from attacks, managing dimensions, and performing grouping. Consequently, we create 24 topic-based models. Assuming normal and spam mail attacks to verify our algorithm, the accuracy of the previous application version was increased by ∼0.4%-1.5%.

show abstract

“…In accordance with Vishagini et al, the researchers have assessed the effect of spam detection using SVM, WSVM with KPCM, and WSVM with KFCM. [16].…”

Section: Parallel Recent Research Outcomesmentioning

confidence: 99%

Detection of Severity-based Email SPAM Messages using Adaptive Threshold Driven Clustering

Venugopal¹,

Bhaskari²,

Seetaramanath³

2022

IJACSA

View full text Add to dashboard Cite

The classification of emails is one crucial part of the email filtering process, as emails have become one of the key methods of communication. The process for identifying safe or unsafe emails is complex due to the diversified use of the language. Nonetheless, most of the parallel research outcomes have demonstrated significant benchmarks in identifying email spam. However, the standard processes can only identify the emails as spam or ham. Henceforth, a detailed classification of the emails has not been achieved. Thus, this work proposes a novel method for the identification of the emails into various classes using the proposed deep clustering process with the help of the ranking of words into severity. The proposed work demonstrates nearly 99.4% accuracy in detecting and classifying the emails into a total of five classes.

show abstract

An Improved Spam Detection Method with Weighted Support Vector Machine

Cited by 19 publications

References 19 publications

Semantic Graph Neural Network: A Conversion from Spam Email Classification to Graph Classification

Semantic Graph Neural Network: A Conversion from Spam Email Classification to Graph Classification

AI-Enabled Grouping Bridgehead to Secure Penetration Topics of Metaverse

Detection of Severity-based Email SPAM Messages using Adaptive Threshold Driven Clustering

Contact Info

Product

Resources

About