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

Pan, Weisen; Li, Jian; Gao, Yixing; Yue, Liexiang; Yang, Yan; Deng, Lingli; Deng, Chao

doi:10.1155/2022/6737080

Cited by 13 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…𝐿 𝑖 = ∑ 𝑀𝑇 𝑖 𝑐 𝑖 + 𝑋 𝑖 𝑛 𝑖=1 (11) Where the IL is exhibited as 𝐿 𝑖 , the input features are depicted as 𝑀𝑇 𝑖 , the weight values are denoted as 𝑐 𝑖 and the bias value is notated as 𝑋 𝑖 .…”

Section: Feature Selection Using Improved Elephant Herd Algorithm (Ieha)mentioning

confidence: 99%

“…However, many of these classifiers have produced noticeable outcomes across a range of datasets. Additionally, a few innovative email classifiers were developed, such as semantic-based classifiers [9], tree-based classifiers [10], and graph-based classifiers [11], to address these issues. But improvement is still required when applied to real- The remainder section of this paper is arranged as follows: section 2 explains the related works.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Email Net: Efficient Email Classification Approach Based on Graph Similarity Measure

2023

IJIES

View full text Add to dashboard Cite

In this Internet Era, Email is a vital form of communication for many academic, personal, and professional users. Despite the availability of alternative means of communication, such as social networks, electronic messages, and mobile apps, email remains an integral part of communication. Email auto-management techniques are necessary for a variety of reasons, such as saving users valuable time, dealing with high-dimensional data, and making email communication easier and more accessible. In this work, a novel email net (improved elephant herd optimization and Graph similarity with the Jaccard index) technique has been proposed for efficient email classification based on graph similarity measure. Initially, the dataset is pre-processed using NLP techniques such as removing email signatures, removing punctuations, removing stop-words, lowercase conversion, tokenization, and stemming for removing irrelevant data. After pre-processing the feature are extracted using bag of words and term frequencyinverse document frequency (TF-IDF). These extracted features are given as input to improved Elephant herding optimization (EHO) for selecting the most relevant features to build a graph-based similarity index for classifying each category of e-mail. The proposed email net was tested on a benchmark dataset and a real-time dataset. Also, the proposed method's performance is compared with other classifiers. According to the experimental results, the proposed approach outperforms all other classifiers with a 98.82% of accuracy.

show abstract

Section: Feature Selection Using Improved Elephant Herd Algorithm (Ieha)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Email Net: Efficient Email Classification Approach Based on Graph Similarity Measure

2023

IJIES

View full text Add to dashboard Cite

show abstract

“…Pan [16] have introduced a semantic graph neural network (SGNN) to overcome the issues related to the classification of spam emails. The SGNN approach changes the email classification problem to a graph classification problem which exhibits the emails in the form of graphs.…”

Section: Related Workmentioning

confidence: 99%

“…The researchers have put forward a step to generate new classification techniques to filter out spam emails and improvise the International Journal of Intelligent Engineering and Systems, Vol. 16 user experience [12,13]. Moreover, the usage of an effective feature selection approach can minimize the dimensionality of the data and helps various machine learning applications [14,15].…”

Section: Introductionmentioning

confidence: 99%

An Efficient Spam Mail Classification Approach Using Improved Moth Flame Optimization and Multi-class Support Vector Machine

2023

IJIES

View full text Add to dashboard Cite

In the modern era, communication through email is increased dramatically due to the cost-effectiveness, usage of contexts, application advertising, and so on. However, e-mails are considered a professional way of communication that helps both commercial and non-commercial organizations to share important documents, reports, and so on. Since e-mail acts as a global pathway, it attracts more intruders to create spam messages which result in storage consumption and virus attacks. To overcome these issues, an improved classification approach is introduced to classify spam emails from ordinary emails. The data is obtained from four benchmark datasets such as Enron, Lingspam, Spamassassin, TREC, and the pre-processing is performed using tokenization, lemmatization, and stemming. After this feature extraction is performed using Bag-of n-grams, latent dirichlet analysis (LDA), term frequency, and inverse document frequency (TF-IDF). Then the feature selection is performed using the proposed improved moth flame optimization (IMFO) algorithm and finally, the classification is performed using multi-class support vector machine (MSVM). The results obtained through experimental analysis show that the proposed IMFO-MSVM has achieved better accuracy of 98.68% whereas the existing semantic graph neural network (SGNN) and fuzzy rule based long short term memory (LSTM) have obtained accuracy of 97.87% and 97% respectively.

show abstract

“…These techniques take the embedded texts from the email body as input, and the outcome is as follows; probable demonstration of a message, whether it is malicious or not. Pan et al [12] presented a model termed Semantic Graph Neural Network (SGNN) to overcome the challenges involved in email classifiers. This approach converted the email classification problems into graph classification problems.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Deep Learning Based Cybersecurity Phishing Email Detection and Classification

Brindha¹,

Nandagopal²,

Azath³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Phishing is a type of cybercrime in which cyber-attackers pose themselves as authorized persons or entities and hack the victims' sensitive data. E-mails, instant messages and phone calls are some of the common modes used in cyberattacks. Though the security models are continuously upgraded to prevent cyberattacks, hackers find innovative ways to target the victims. In this background, there is a drastic increase observed in the number of phishing emails sent to potential targets. This scenario necessitates the importance of designing an effective classification model. Though numerous conventional models are available in the literature for proficient classification of phishing emails, the Machine Learning (ML) techniques and the Deep Learning (DL) models have been employed in the literature. The current study presents an Intelligent Cuckoo Search (CS) Optimization Algorithm with a Deep Learning-based Phishing Email Detection and Classification (ICSOA-DLPEC) model. The aim of the proposed ICSOA-DLPEC model is to effectually distinguish the emails as either legitimate or phishing ones. At the initial stage, the pre-processing is performed through three stages such as email cleaning, tokenization and stop-word elimination. Then, the N-gram approach is; moreover, the CS algorithm is applied to extract the useful feature vectors. Moreover, the CS algorithm is employed with the Gated Recurrent Unit (GRU) model to detect and classify phishing emails. Furthermore, the CS algorithm is used to fine-tune the parameters involved in the GRU model. The performance of the proposed ICSOA-DLPEC model was experimentally validated using a benchmark dataset, and the results were assessed under several dimensions. Extensive comparative studies were conducted, and the results confirmed the superior performance of the proposed ICSOA-DLPEC model over other existing approaches. The proposed model achieved a maximum accuracy of 99.72%.

show abstract

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

Cited by 13 publications

References 22 publications

Email Net: Efficient Email Classification Approach Based on Graph Similarity Measure

Email Net: Efficient Email Classification Approach Based on Graph Similarity Measure

An Efficient Spam Mail Classification Approach Using Improved Moth Flame Optimization and Multi-class Support Vector Machine

Intelligent Deep Learning Based Cybersecurity Phishing Email Detection and Classification

Contact Info

Product

Resources

About