Dynamic Recognition of Phishing URLs Using Deep Learning Techniques

Sountharrajan, S.; Nivashini, M.; Shandilya, Shishir Kumar; Suganya, E.; Banu, Ayesha; Karthiga, M.

doi:10.1007/978-3-030-19353-9_3

Cited by 17 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a single classifier, DNN was used in [18][19][20] to train the classification system for the detection of phishing websites. Instead of using DNN as a stand-alone classifier, the authors in [21,22] combined it with other DL algorithms to build a model to differentiate between malicious and benign URLs. It was observed that among these DNN-based models, parameters settings play an essential role in determining the system's performance accuracy.…”

Section: Deep Neural Network (Dnn)mentioning

confidence: 99%

“…It was observed that among these DNN-based models, parameters settings play an essential role in determining the system's performance accuracy. Nevertheless, some studies [21,22] did not mention any of the hyper-parameters in the design of the neural network architecture, while other papers [19,20] only specified a few of them without performing parameter optimization. The authors in [18] made additional effort in fine-tuning the parameters, but not all were included.…”

Section: Deep Neural Network (Dnn)mentioning

confidence: 99%

“…Previous studies have shown a limited number of metrics were used to assess the performance of DL models in detecting phishing websites. For example, only two metrics were used in [19], and three were measured in [21]. More metrics were used in the studies [18,22], yet only the selected ones were utilized to benchmark with other machine learning classifiers.…”

Section: Deep Neural Network (Dnn)mentioning

confidence: 99%

See 2 more Smart Citations

Phishing Webpage Classification via Deep Learning-Based Algorithms: An Empirical Study

Selamat

Krejcar

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Phishing detection with high-performance accuracy and low computational complexity has always been a topic of great interest. New technologies have been developed to improve the phishing detection rate and reduce computational constraints in recent years. However, one solution is insufficient to address all problems caused by attackers in cyberspace. Therefore, the primary objective of this paper is to analyze the performance of various deep learning algorithms in detecting phishing activities. This analysis will help organizations or individuals select and adopt the proper solution according to their technological needs and specific applications’ requirements to fight against phishing attacks. In this regard, an empirical study was conducted using four different deep learning algorithms, including deep neural network (DNN), convolutional neural network (CNN), Long Short-Term Memory (LSTM), and gated recurrent unit (GRU). To analyze the behaviors of these deep learning architectures, extensive experiments were carried out to examine the impact of parameter tuning on the performance accuracy of the deep learning models. In addition, various performance metrics were measured to evaluate the effectiveness and feasibility of DL models in detecting phishing activities. The results obtained from the experiments showed that no single DL algorithm achieved the best measures across all performance metrics. The empirical findings from this paper also manifest several issues and suggest future research directions related to deep learning in the phishing detection domain.

show abstract

Section: Deep Neural Network (Dnn)mentioning

confidence: 99%

Section: Deep Neural Network (Dnn)mentioning

confidence: 99%

Section: Deep Neural Network (Dnn)mentioning

confidence: 99%

See 1 more Smart Citation

Phishing Webpage Classification via Deep Learning-Based Algorithms: An Empirical Study

Selamat

Krejcar

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In addition, the researchers tend to worn on reducing the candidate pattern size (20). The various optimization techniques used in classification is proposed in (21)(22)(23). The low frequency itemsets play a vital role in assessing the profit of a business, using which the low frequency items can be recommended for offer sale.…”

Section: Related Artmentioning

confidence: 99%

Top ‘N’ Variant Random Forest Model for High Utility Itemsets Recommendation

Pazhaniraja¹,

Sountharrajan²,

Suganya³

et al. 2018

EAI Endorsed Transactions on Energy Web

View full text Add to dashboard Cite

High-utility based itemset mining is the advancement of recurrent pattern mining that discovers occurrence of frequent transactions from a huge database. The issues in frequent pattern mining involve the elimination of quantities purchased by the customers and cost of purchased product. This can be resolved by high utility itemset mining which includes quantities and profit of the products in the transactions. The conventional association rule mining algorithms results in huge memory consumption due to the complexity in pruning the search space. In this paper, machine learning based high-utility itemset mining is applied to predict next order in an online grocery store depending on the transactions. The overall goal is to enhance the business profitability by stocking the high utility items in market. The Top 'N' variant Random Forest model is proposed to recommend the high utility itemsets, thereby predicting the reordered/next ordered items. The model is evaluated using Instacart market dataset to measure accuracy, precision and recall.

show abstract

“…Words and phrases are expressed as vectors in the single-granularity tiny content semantic similarity prototype and the sentence likeness esteem is obtained by determining vector similarity using Deep Structured Semantic Model [2], Convolutional Latent Semantic Model [3], and LSTM-Recurrent Neural Network. The prototype on multigranularity text similarity [4] model is based upon the single-greyscale textual semantic closeness, and not only words/ phrases but also its combinations are considered for text representation such as Multi-Granularity Convolution Neural Network model [5] , and the Multi Variable-Long Short Term Memory technique [6]. Semantic likeness detection in English sentences using the above two models results in two issues: 1) Single grouping methodology cannot manage the problem of polysemous words and synonymously equivalent words.…”

Section: Introductionmentioning

confidence: 99%

Sentence Semantic Similarity Model Using Convolutional Neural Networks

Karthiga¹,

Sountharrajan²,

Suganya³

et al. 2018

EAI Endorsed Transactions on Energy Web

View full text Add to dashboard Cite

In Natural Language Processing, determining the semantic likeness between sentences is an important research area. For example, there exists many possible semantics for a word (polysemy), and the synonym of the word differs. Double LSTM (Long Short Term Memory) working at same time on double phrase sequences model is projected to overcome the solitary sequence problem. Furthermore, with the goal of overcoming the second issue, as indicated by the qualities of English dialect, we utilized the British corpus semantic similarity datasets structured by specialists to prepare, and validate the technique. During the training process the stop words were reserved for use. Convolution Neural Network and Semantic Likeness model based on grammar are used to compare the results of our projected representation. The outcomes demonstrate that the proposed methodology is more prominent than the previous approaches by means of precision, recall rate, accuracy etc., along with the enhanced generalization potential of the neural network.

show abstract

Dynamic Recognition of Phishing URLs Using Deep Learning Techniques

Cited by 17 publications

References 9 publications

Phishing Webpage Classification via Deep Learning-Based Algorithms: An Empirical Study

Phishing Webpage Classification via Deep Learning-Based Algorithms: An Empirical Study

Top ‘N’ Variant Random Forest Model for High Utility Itemsets Recommendation

Sentence Semantic Similarity Model Using Convolutional Neural Networks

Contact Info

Product

Resources

About