Phishing e-mail detection by using deep learning algorithms

Hassanpour, Reza; Doğdu, Erdoğan; Choupani, Roya; Goker, Onur; Nazli, Nazli

doi:10.1145/3190645.3190719

Cited by 20 publications

(12 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many pieces of research aimed to develop applications that can correctly detect phishing cases [3]- [6]. Some of them focus on the phishing sites detection [7]- [10], whereas other part focus on the phishing e-mails detection [11]- [13]. This paper is concentrated on phishing e-mail detection.…”

Section: Introductionmentioning

confidence: 99%

“…Instead of selecting more representative features, or performing mathematical transformations or probabilistic calculations on the VSM representation to extract more distinctive features, representing such texts in a fixed shared low dimensional space, also called distributed models [13], [24]- [26], is also an approach. In this paradigm, a vector and its pre-fixed dimensions represent a word and its contextual information (such as relations with other words, and its semantic and syntactic similarities).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

From Feature Engineering and Topics Models to Enhanced Prediction Rates in Phishing Detection

et al. 2020

View full text Add to dashboard Cite

Phishing is a type of fraud attempt in which the attacker, usually by e-mail, pretends to be a trusted person or entity in order to obtain sensitive information from a target. Most recent phishing detection researches have focused on obtaining highly distinctive features from the metadata and text of these e-mails. The obtained attributes are then used to feed classification algorithms in order to determine whether they are phishing or legitimate messages. In this paper, it is proposed an approach based on machine learning to detect phishing e-mail attacks. The methods that compose this approach are performed through a feature engineering process based on natural language processing, lemmatization, topics modeling, improved learning techniques for resampling and cross-validation, and hyperparameters configuration. The first proposed method uses all the features obtained from the Document-Term Matrix (DTM) in the classification algorithms. The second one uses Latent Dirichlet Allocation (LDA) as an operation to deal with the problems of the ''curse of dimensionality'', the sparsity, and the text context portion included in the obtained representation. The proposed approach reached marks with an F1-measure of 99.95% success rate using the XGBoost algorithm. It outperforms state-of-the-art phishing detection researches for an accredited data set, in applications based only on the body of the e-mails, without using other e-mail features such as its header, IP information or number of links in the text.INDEX TERMS Feature engineering, feature extraction, natural language processing, phishing detection, topics modeling, XGBoost.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

From Feature Engineering and Topics Models to Enhanced Prediction Rates in Phishing Detection

et al. 2020

View full text Add to dashboard Cite

show abstract

“…At this stage, from the features attributes provided by the feature engineering phase, models are trained to properly fit the e-mail characteristics, achieving a discriminating function to classify 13 these e-mails instances as legitimate or phishing e-mail. The obtained features sets are derived from two methods, Method 1 and Method 2, each with two perspectives (using a different technique in each of them), as stated earlier.…”

Section: J Features Attributesmentioning

confidence: 99%

“…Therefore, the detection of this type of e-mail is critical to counter these attacks. Currently, as pointed in [8], [9], [10] and [7], phishing detecting mechanisms based on Natural Language Processing (NLP) and Machine Learning (ML) techniques, such as [11], [12] and [13], are an effective way to defend against this type of threat, since such approaches exploit the morphology and semantics of the text.…”

Section: Introductionmentioning

confidence: 99%

The Answer is in the Text: Multi-Stage Methods for Phishing Detection Based on Feature Engineering

et al. 2020

View full text Add to dashboard Cite

“…Hassanpour et al [46] displayed the email material as highlights in the Word2-Vec format utilizing certain deep learning tools, and developers have achieved 97 percent of general accuracy.…”

Section: Literature Surveymentioning

confidence: 99%

Classification of Social Media Text Spam Using VAE-CNN and LSTM Model

Metlapalli¹,

Muthusamy²,

Battula³

2020

ISI

View full text Add to dashboard Cite

Presently a day's human relations are kept up by online life systems. Customary connections now days are outdated. To keep up in affiliation, sharing thoughts, trade information between we utilize web-based social networking organizing locales. Web based life organizing locales like Twitter, Facebook, LinkedIn and so forth are accessible in the correspondence condition. Through Twitter media clients share their sentiments, interests, information to others by messages. Simultaneously a portion of the client's mislead the certifiable clients. These certified clients are additionally called requested clients and the clients what misguidance's identity is called spammers. These spammers present undesirable data on the non-spam clients. The non-spammers may retweet them to other people and they follow the spammers. Generally most of the spam messages are in the form of text, images and different multimedia formats. Considering all different formats in one process may not give the best classification results. In this paper address the process and classification of text spam messages. Classification of text messages is a complex task in order to achieve this deep learning based hybrid VAE-CNN and LSTM model is proposed and evaluated the model using the performance metrics of precision, recall and F measure metrics.

show abstract

Phishing e-mail detection by using deep learning algorithms

Cited by 20 publications

References 0 publications

From Feature Engineering and Topics Models to Enhanced Prediction Rates in Phishing Detection

From Feature Engineering and Topics Models to Enhanced Prediction Rates in Phishing Detection

The Answer is in the Text: Multi-Stage Methods for Phishing Detection Based on Feature Engineering

Classification of Social Media Text Spam Using VAE-CNN and LSTM Model

Contact Info

Product

Resources

About