60 Hits in 6.3 sec

A Deep Learning Model with Hierarchical LSTMs and Supervised Attention for Anti-Phishing [article]

Minh Nguyen, Toan Nguyen, Thien Huu Nguyen
2018 arXiv   pre-print
In particular, we present a framework with hierarchical long short-term memory networks (H-LSTMs) and attention mechanisms to model the emails simultaneously at the word and the sentence level.  ...  Our expectation is to produce an effective model for anti-phishing and demonstrate the effectiveness of deep learning for problems in cybersecurity.  ...  We present a new deep learning model to solve the problem of email phishing prediction using hierarchical long shortterm memory networks (H-LSTMs) augmented with supervised attention technique.  ... 
arXiv:1805.01554v1 fatcat:d25stxadzfbmfjkvw234gim4ia

Federated Phish Bowl: LSTM-Based Decentralized Phishing Email Detection [article]

Yuwei Sun, Ng Chong, Hideya Ochiai
2022 arXiv   pre-print
Using long short-term memory (LSTM) for phishing detection, the framework adapts by sharing a global word embedding matrix across the clients, with each client running its local model with Non-IID data  ...  In particular, we devise a knowledge-sharing mechanism with federated learning (FL).  ...  [4] proposed a hierarchical attentive long short-term memory (LSTM)-based detection method that models the email bodies at the word level and the sentence level while leveraging a supervised attention  ... 
arXiv:2110.06025v2 fatcat:5ttojciqd5cvnjnqdktnyxnmnu

Modeling Coherency in Generated Emails by Leveraging Deep Neural Learners [article]

Avisha Das, Rakesh M. Verma
2020 arXiv   pre-print
The method used leverages a hierarchical deep neural model which uses a learned representation of the sentences in the input document to generate structured written emails.  ...  We demonstrate the generation of short and targeted text messages using the deep model.  ...  Army Research Laboratory and the U. S. Army Research Office under contract/grant number W911NF-16-1-0422.  ... 
arXiv:2007.07403v1 fatcat:bkpoc5spsrelhbal3skitz2m44

Deep Learning for Phishing Detection: Taxonomy, Current Challenges and Future Directions

Nguyet Quang Do, Ali Selamat, Ondrej Krejcar, Enrique Herrera-Viedma, Hamido Fujita
2022 IEEE Access  
In recent years, deep learning has emerged as a branch of machine learning that has become a promising solution for phishing detection.  ...  As a result, this study proposes a taxonomy of deep learning algorithms for phishing detection by examining 81 selected papers using a systematic literature review approach.  ...  Detection Websites Conference paper Mitigating Email Phishing Attacks using Convolutional Neural Networks 1 A Deep Learning Model with Hierarchical LSTMs and Supervised Attention for Anti-Phishing 10  ... 
doi:10.1109/access.2022.3151903 fatcat:hhuywvlz5bac5fc5eoizyam77i

Web2Vec: Phishing Webpage Detection Method Based on Multidimensional Features Driven by Deep Learning

Jian Feng, Lian-yang Zou, Ou Ye, Jing-zhou Han
2020 IEEE Access  
CONCLUSIONS A phishing webpage detection model Web2Vec based on representation learning and deep learning is proposed in the paper.  ...  to automatically learn the representation of the webpages in all dimensions. • A hybrid deep learning model that fuses CNN, BiLSTM, and attention is represented. • Further, four experiments on the Web2Vec  ... 
doi:10.1109/access.2020.3043188 fatcat:3uno5f3c2vdc3itgxijhsxhzwi

Phishing Email Detection Using Improved RCNN Model With Multilevel Vectors and Attention Mechanism

Yong Fang, Cheng Zhang, Cheng Huang, Liang Liu, Yue Yang
2019 IEEE Access  
Then, based on an improved recurrent convolutional neural networks (RCNN) model with multilevel vectors and attention mechanism, we proposed a new phishing email detection model named THEMIS, which is  ...  High accuracy and low FPR ensure that the filter can identify phishing emails with high probability and filter out legitimate emails as little as possible.  ...  ACKNOWLEDGMENT The authors would like to thank IWSPA-AP 2018 for providing experimental data in this research.  ... 
doi:10.1109/access.2019.2913705 fatcat:zrek2e4pvrholi52k42dt2s4x4

Optimal Deep Belief Network Enabled Cybersecurity Phishing Email Classification

Ashit Kumar Dutta, T. Meyyappan, Basit Qureshi, Majed Alsanea, Anas Waleed Abulfaraj, Manal M. Al Faraj, Abdul Rahaman Wahab Sait
2023 Computer systems science and engineering  
This article focuses on the design of biogeography based optimization with deep learning for Phishing Email detection and classification (BBODL-PEDC) model.  ...  Moreover, optimal deep belief network (DBN) model is used for the email classification and its efficacy can be boosted by the BBO based hyperparameter tuning process.  ...  The authors would like to acknowledge the support of Prince Sultan University for paying the Article Processing Charges (APC) of this publication.  ... 
doi:10.32604/csse.2023.028984 fatcat:xsyrum6nubaa3a4bytp6wjmwju

Classification of Phishing Email Using Word Embedding and Machine Learning Techniques

Somesha M., Alwyn R. Pais
2022 Journal of Cyber Security and Mobility  
Hence there is a need for real-time input data set to design accurate email anti-phishing solutions.  ...  In the current work, it has been created a real-time in-house corpus of phishing and legitimate emails and proposed efficient techniques to detect phishing emails using a word embedding and machine learning  ...  Nguyen et al [28] presented a deep learning model with hierarchical-LSTM and a supervised attention mechanism.  ... 
doi:10.13052/jcsm2245-1439.1131 fatcat:7pyymzkh3zfwfallb72ucjvbke

Lumen: A machine learning framework to expose influence cues in texts

Hanyu Shi, Mirela Silva, Luiz Giovanini, Daniel Capecci, Lauren Czech, Juliana Fernandes, Daniela Oliveira
2022 Frontiers in Computer Science  
Evaluation of Lumen in comparison to other learning models showed that Lumen and LSTM presented the best F1-micro score, but Lumen yielded better interpretability.  ...  Lumen was trained with a newly developed dataset of 3K texts comprised of disinformation, phishing, hyperpartisan news, and mainstream news.  ...  Acknowledgments The authors would like to thank the coders for having helped with the labeling of the influences cues in our dataset.  ... 
doi:10.3389/fcomp.2022.929515 fatcat:xavvp2clqrcwpjqvbxg5fgevzu

Security Threats and Artificial Intelligence based Countermeasures for Internet of Things Networks: A Comprehensive Survey

Shakila Zaman, Khaled Alhazmi, Mohammed Aseeri, Muhammad Raisuddin Ahmed, Risala Tasin Khan, M. Shamim Kaiser, Mufti Mahmud
2021 IEEE Access  
learning is better than deep and linear learning methods.  ...  Shallow ML RF Tree based Supervised ensemble learning model which construct a multitude of DT to predict the output.  ...  This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see  ... 
doi:10.1109/access.2021.3089681 fatcat:fatpywnjzzfilidakyduz6qz44

Phishing URL detection: A real-case scenario through login URLs

Manuel Sanchez-Paniagua, Eduardo Fidalgo, Enrique Alegre, Al-Nabki Mhd Wesam, Victor Gonzalez-Castro
2022 IEEE Access  
In this paper, we compare machine learning and deep learning techniques to present a method capable of detecting phishing websites through URL analysis.  ...  Additionally, we use datasets from different years to show how models decrease their accuracy over time by training a base model with old datasets and testing it with recent URLs.  ...  ACKNOWLEDGMENT The authors gratefully acknowledge the support of Nvidia Corporation for their kind donation of GPUs (GeForce GTX Titan X and K-40) that were used in this work.  ... 
doi:10.1109/access.2022.3168681 fatcat:5etylzjttfhdzj6wsy5wjbf7ea

An Effective Phishing Detection Model Based on Character Level Convolutional Neural Network from URL

Ali Aljofey, Qingshan Jiang, Qiang Qu, Mingqing Huang, Jean-Pierre Niyigena
2020 Electronics  
In this paper, a fast deep learning-based solution model, which uses character-level convolutional neural network (CNN) for phishing detection based on the URL of the website, is proposed.  ...  For evaluations, comparisons are provided between different traditional machine learning models and deep learning models using various feature sets such as hand-crafted, character embedding, character  ...  Finally, the advantage of classification supervised machine learning algorithms is used to develop a model for phishing detection.  ... 
doi:10.3390/electronics9091514 fatcat:ermf5orptrf75msi25mpnrx3yy

Machine Learning for Web Page Classification: A Survey

safae lassri, EL HABIB BENLAHMAR, Abderrahim TRAGHA
2019 International Journal of Information Science and Technology  
from ScienceDirect and Springer websites, we review the different machine learning algorithms used to categorize web pages.  ...  To exploit this data, a Web information retrieval system and a categorization of internet content based on the classification of web pages are essential.  ...  98.25% and a micro-averaged F1 score of 0.98 much higher than the other deep learning model and feature-engineer model (SdA-SVM, SVM, LSTM, Bayes) 91.85% accuracy for individual image categorization and  ... 
doaj:483a4b9f259046a29c57adc3021a50d0 fatcat:hdznsdeotnhwpgpuigi7iovhja

Lumen: A Machine Learning Framework to Expose Influence Cues in Text [article]

Hanyu Shi, Mirela Silva, Daniel Capecci, Luiz Giovanini, Lauren Czech, Juliana Fernandes, Daniela Oliveira
2021 arXiv   pre-print
Evaluation of Lumen in comparison to other learning models showed that Lumen and LSTM presented the best F1-micro score, but Lumen yielded better interpretability.  ...  Lumen was trained with a newly developed dataset of 3K texts comprised of disinformation, phishing, hyperpartisan news, and mainstream news.  ...  ACKNOWLEDGMENTS The authors would like to thank the coders for having helped with the labeling of the influences cues in our dataset. This work was support by the University  ... 
arXiv:2107.10655v1 fatcat:lolcasufhjav7dctmnpeqp6m5q

Cybersecurity Threats and Their Mitigation Approaches Using Machine Learning—A Review

Mostofa Ahsan, Kendall E. Nygard, Rahul Gomes, Md Minhaz Chowdhury, Nafiz Rifat, Jayden F Connolly
2022 Journal of Cybersecurity and Privacy  
The detection of hidden trends and insights from network data and building of a corresponding data-driven machine learning model to prevent these attacks is vital to design intelligent security systems  ...  Several machine learning and statistical methods, such as deep learning, support vector machines and Bayesian classification, among others, have proven effective in mitigating cyber-attacks.  ...  As a result, deep learning algorithms are more effective and need less data processing. For large datasets, deep learning methods have a significant advantage over classical machine learning models.  ... 
doi:10.3390/jcp2030027 fatcat:3m3rxixzjjcwbhzk2od72xatta
« Previous Showing results 1 — 15 out of 60 results