Visual and textual features based email spam classification using S-Cuckoo search and hybrid kernel support vector machine

Kumaresan, T.; Saravanakumar, S.; Balamurugan, R.

doi:10.1007/s10586-017-1615-8

Cited by 24 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LIBSVM Support vector machine tool [12] is used to simulate the results and data is converted to SVM Data format. Training and test data sets are organized in the following format for the purpose of using LibSVM tool.…”

Section: Experimentation Results and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Genre Categorization of Emails into predefined categories using machine learning

Bhalla¹

2021

TURCOMAT

View full text Add to dashboard Cite

In today’s dynamic world, there is a need for fast, efficient, and reliable means of communication. To meet these requirements email system was developed and it got popular with the invention of WWW. Now, the Email system has been used extensively for official, business, and personal communication. On average individual users receive 50-60 mails each day. It is becoming a burden to easily manage emails. So there is a need for effective and reliable means to organize the mails for easy and fast retrieval. An efficient approach is proposed in this paper to classify the mails based on the predefined genres. It has been observed in the proposed research that the classification of emails greatly improves efficiency and saves time and effort to manage them. The results obtained in this paper are very encouraging. Over 90 % of emails are categorized correctly. Email genres are predefined and corresponding keyword lists are generated. Frequency tf-idf of the keywords in the email decides the genre of mail. SVM is used as a multiclass classifier. In this paper need for negative training data has been removed as the proposed classifier works on the principle of one class against the rest.

show abstract

Section: Experimentation Results and Discussionmentioning

confidence: 99%

“…Hence, the research work may be used in categorization of large number of categories of emails. Overall results yield the superior performance as indicated in figures [12,13] through Receiver operating curve (ROC).…”

Section: Fig12: Auc Curve-training Datamentioning

confidence: 99%

Automatic Genre Categorization of Emails into predefined categories using machine learning

Bhalla¹

2021

TURCOMAT

View full text Add to dashboard Cite

show abstract

“…However, main advantage of this approach was its highest accuracy, but failed to detect the spam messages effectively. Kumaresan T [28] et al introduced a spam categorization strategy called S-Cuckoo and hybrid kernelbased support vector machine (HKSVM). This method involved mainly three phases, namely textual and visual feature extraction, best feature selection, and spam classification.…”

Section: Related Workmentioning

confidence: 99%

“…In addition to this, it also consumes lot of user's valuable time as well as provoking them to detect and destroy the unnecessary messages. Thus, spam detection still remains as one of the challenging tasks for many organizations [28]. However, there have been different types of methods to alleviate the quantity of spam.…”

Section: Introductionmentioning

confidence: 99%

Untitled

2021

INDJCSE

View full text Add to dashboard Cite

Phishing attack is acclaimed as one of the recognized cybercrime attacks over the internet and mail users. Phishing is a form of unauthorized access of confidential information, like passwords, user names and credit card details. Detection of phishing attacks and classifying the mails still remains a challenging issue. This research presents an effective strategy by developing a newly proposed method called Fractional-EarthWorm Algorithm (EWA) based Deep Convolutional Neural Network. The Fractional-EWA is derived by inclusion of fractional calculus concept to EarthWorm Optimization. The features are extracted using the term frequency and the feature is selected using the Levenshtein distance. The DCNN is trained by exploiting the proposed Fractional-EWA. However, this algorithm achieved maximum accuracy, maximum sensitivity, and maximum specificity of 0.781, 0.782, and 0.722 respectively for chunk percentage of data and achieved the maximum accuracy, maximum sensitivity, and maximum specificity of 0.744, 0.725, and 0.723, respectively for number of features.

show abstract

“…Social engineering and enterprise security continue to be significant because organizations progressively have observed a vulnerable link exists in the security chain (Bongiorno et al, 2018). Without employing risk mitigation controls, many organizations would be unable to monitor well-known threats, recognize new threats, and gauge existing processes effectively (Kumaresan et al, 2017). Therefore, demonstrating why organizations are apprehensive about integrating external applications and services into their existing organizational infrastructure (Janssen et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

The Effects Of Social Engineering On Enterprise Security

Jackson¹

2021

Scha

View full text Add to dashboard Cite

The focus of this research was to explore present control methods and solutions used throughout technology-based, healthcare-based, and manufacturing-based organizations in southwest Georgia to determine their effectiveness for reducing potential threats. Semi-structured interviews with open-ended questions are used to explore 30 information technology professionals' lived experiences with IT security policies and procedures. Two research questions guided the qualitative exploratory case study: How important is social engineering and enterprise security to the organization? and How are organizations evaluating and managing existing organizational solutions? Several themes emerged: (a) lack of education and inadequate information can affect the decision-making process, (b) response times from management is a key factor in reducing threats, (c) a sense of failure is always present, (d) failed IT policy management can increase organizational vulnerability, and (e) social engineering still has a negative stigma in the business environment. The findings suggest that although steps were made to change the perception of social engineering and enterprise security, additional work is needed to ensure employees are aware of how social engineering and enterprise security can affect their organization productivity. Key Words: Information systems, information technology, social engineering, enterprise security, control methods, policies, procedures, management

show abstract

Visual and textual features based email spam classification using S-Cuckoo search and hybrid kernel support vector machine

Cited by 24 publications

References 41 publications

Automatic Genre Categorization of Emails into predefined categories using machine learning

Automatic Genre Categorization of Emails into predefined categories using machine learning

Untitled

The Effects Of Social Engineering On Enterprise Security

Contact Info

Product

Resources

About