Analysis and Prevention of AI-Based Phishing Email Attacks
Open accessThe DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.
Abstract
Phishing email attacks are among the most common and most harmful cybersecurity attacks. With the emergence of generative AI, phishing attacks can be based on emails generated automatically, making it more difficult to detect them. That is, instead of a single email format sent to a large number of recipients, generative AI can be used to send each potential victim a different email, making it more difficult for cybersecurity systems to identify the scam email before it reaches the recipient. Here, we describe a corpus of AI-generated phishing emails. We also use different machine learning tools to test the ability of automatic text analysis to identify AI-generated phishing emails. The results are encouraging, and show that machine learning tools can identify an AI-generated phishing email with high accuracy compared to regular emails or human-generated scam emails. By applying descriptive analytics, the specific differences between AI-generated emails and manually crafted scam emails are profiled and show that AI-generated emails are different in their style from human-generated phishing email scams. Therefore, automatic identification tools can be used as a warning for the user. The paper also describes the corpus of AI-generated phishing emails that are made open to the public and can be used for consequent studies. While the ability of machine learning to detect AI-generated phishing emails is encouraging, AI-generated phishing emails are different from regular phishing…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“AI Agents are purpose-built for narrow, and well-defined tasks [65,66]. They are optimized to execute repeatable operations within a fixed domain, such as email filtering [67, 68], database querying [69], or calendar coordination [44,70].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [67]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“The neural network is relatively simple, and based on the common Long Short Term Memory (LSTM) architecture (Hochreiter and Schmidhuber, 1997).”
MethodThe Stanford CoreNLP Natural Language Processing Toolkit
Manning, C., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S., & McClosky, D. (2014) · Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.3115/v1/p14-5010 · Cited by 7,037 · cited 2×
“The sentiments of the text is estimated by applying the sentiment analysis of CoreNLP (Manning et al., 2014) score between 0 through 4, where 0 means very negative and 4 means very positive.”
BackgroundMethodThe Enron Corpus: A New Dataset for Email Classification Research
Klimt, B., & Yang, Y. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-30115-8_22 · Cited by 1,157 · cited 1×
“The first is the Enron email dataset (Diesner and Carley, 2005; Minkov et al., 2008; Shetty and Adibi, 2004; Klimt and Yang, 2004), which is used as a dataset of “regular” email messages.”
MethodPhishing Detection: A Literature Survey
Khonji, M., Iraqi, Y., & Jones, A. (2013) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2013.032213.00009 · Cited by 605 · cited 1×
“A phishing email attack (Fette et al., 2007; Hong, 2012; Khonji et al., 2013; Almomani et al., 2013; Parsons et al., 2019; Patel et al., 2019; Stojnic et al., 2021; Do et al., 2022) is a form of cybersecurity attack in which the attacker contacts a potential victim through an email message that…”
BackgroundLearning to detect phishing emails
Fette, I., Sadeh, N., & Tomasic, A. (2007) · Proceedings of the 16th international conference on World Wide Web · doi:10.1145/1242572.1242660 · Cited by 604 · cited 1×
“A phishing email attack (Fette et al., 2007; Hong, 2012; Khonji et al., 2013; Almomani et al., 2013; Parsons et al., 2019; Patel et al., 2019; Stojnic et al., 2021; Do et al., 2022) is a form of cybersecurity attack in which the attacker contacts a potential victim through an email message that…”
BackgroundHong, J. (2012) · Communications of the ACM · doi:10.1145/2063176.2063197 · Cited by 551 · cited 1×
“A phishing email attack (Fette et al., 2007; Hong, 2012; Khonji et al., 2013; Almomani et al., 2013; Parsons et al., 2019; Patel et al., 2019; Stojnic et al., 2021; Do et al., 2022) is a form of cybersecurity attack in which the attacker contacts a potential victim through an email message that…”
BackgroundA comparison of machine learning techniques for phishing detection
Abu-Nimeh, S., Nappa, D., Wang, X., & Nair, S. (2007) · Proceedings of the anti-phishing working groups 2nd annual eCrime researchers summit · doi:10.1145/1299015.1299021 · Cited by 502 · cited 1×
“Other approaches are based on natural language processing of the email content (Abu-Nimeh et al., 2007; Verma et al., 2012; Almomani et al., 2013; Al-hogail and Alsabih, 2021; Salloum et al., 2022).”
BackgroundThe Enron Email Dataset Database Schema and Brief Statistical Report
Shetty, J., & Adibi, J. (2004) · Cited by 315
A Survey of Phishing Email Filtering Techniques
Almomani, A., Gupta, B. B., Atawneh, S., Meulenberg, A., & Almomani, E. (2013) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2013.030713.00020 · Cited by 272 · cited 2×
“Other approaches are based on natural language processing of the email content (Abu-Nimeh et al., 2007; Verma et al., 2012; Almomani et al., 2013; Al-hogail and Alsabih, 2021; Salloum et al., 2022).”
BackgroundWND-CHARM: Multi-purpose image classification using compound image transforms
Orlov, N., Shamir, L., Macura, T., Johnston, J., Eckley, D. M., & Goldberg, I. G. (2008) · Pattern Recognition Letters · doi:10.1016/j.patrec.2008.04.013 · Cited by 265 · cited 2×
“That is done through UDAT by using the Linear Discriminant Analysis (LDA) scores of the features (Orlov et al., 2008).”
MethodSelf-citationFerrara, E. (2024) · Journal of Computational Social Science · doi:10.1007/s42001-024-00250-1 · Cited by 259 · cited 1×
“The ability to create fake identities can be used to spread false information, or harass specific targeted victims (Ferrara, 2024).”
BackgroundSamuelson, P. (2023) · Science · doi:10.1126/science.adi0656 · Cited by 240 · cited 1×
“That is done by using copyrighted art for training generative AI systems, that consequently generate work heavily based on the copyrighted art it was trained with (Franceschelli and Musolesi, 2022; Samuelson, 2023).”
MethodDeep Learning for Phishing Detection: Taxonomy, Current Challenges and Future Directions
Do, N. Q., Selamat, A., Krejcar, O., Herrera-Viedma, E., & Fujita, H. (2022) · IEEE Access · doi:10.1109/access.2022.3151903 · Cited by 221 · cited 1×
“…attack (Fette et al., 2007; Hong, 2012; Khonji et al., 2013; Almomani et al., 2013; Parsons et al., 2019; Patel et al., 2019; Stojnic et al., 2021; Do et al., 2022) is a form of cybersecurity attack in which the attacker contacts a potential victim through an email message that deceives the…”
BackgroundSalloum, S., Gaber, T., Vadera, S., & Shaalan, K. (2022) · IEEE Access · doi:10.1109/access.2022.3183083 · Cited by 210 · cited 1×
“Other approaches are based on natural language processing of the email content (Abu-Nimeh et al., 2007; Verma et al., 2012; Almomani et al., 2013; Al-hogail and Alsabih, 2021; Salloum et al., 2022).”
BackgroundA Memory-Based Approach to Anti-Spam Filtering for Mailing Lists
Sakkis, G., Androutsopoulos, I., Paliouras, G., Karkaletsis, V., Spyropoulos, C. D., & Stamatopoulos, P. (2003) · Information Retrieval · doi:10.1023/a:1022948414856 · Cited by 207 · cited 1×
“3 https://www.cs.cmu.edu/ ~enron/ In addition to these datasets, we also used the Ling-Spam dataset (Sakkis et al., 2003; Deshpande et al., 2007) as a dataset of manually crafted regular and spam emails.”
MethodApplying machine learning and natural language processing to detect phishing email
Alhogail, A., & Alsabih, A. (2021) · Computers & Security · doi:10.1016/j.cose.2021.102414 · Cited by 182
Automatic Categorization of Email into Folders: Benchmark Experiments on Enron and SRI Corpora
Bekkerman, R., McCallum, A., & Huang, G. B. (2005) · ScholarWorks@UMassAmherst (University of Massachusetts Amherst) · Cited by 179
New filtering approaches for phishing email
Bergholz, A., De Beer, J., Glahn, S., Moens, M.-F., Paaß, G., & Strobel, S. (2010) · Journal of Computer Security · doi:10.3233/jcs-2010-0371 · Cited by 177 · cited 1×
“These pieces of information can be combined with machine learning to identify phishing emails (Cranor et al., 2006; Bergholz et al., 2010).”
BackgroundPhishing Email Detection Using Improved RCNN Model With Multilevel Vectors and Attention Mechanism
Fang, Y., Zhang, C., Huang, C., Liu, L., & Yang, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2913705 · Cited by 177 · cited 1×
“…Machines (SVM) (Niu et al., 2017), J48 (Smadi et al., 2015), random forest (HR et al., 2020), recurrent convolutional neural networks (RCNNs) (Fang et al., 2019), and other deep neural network architectures (Yerima and Alza-ylaee, 2020; Magdy et al., 2022; Rathee and Mann, 2022; Bagui et…”
BackgroundDeep fake detection and classification using error-level analysis and deep learning
Rafique, R., Gantassi, R., Amin, R., Frnda, J., Mustapha, A., & Alshehri, A. H. (2023) · Scientific Reports · doi:10.1038/s41598-023-34629-3 · Cited by 155 · cited 1×
“For instance, the ability to create realistic “deep fake” images, videos and audio can be used to disseminate false information (Sug-anthi et al., 2022; Rafique et al., 2023).”
BackgroundPredicting susceptibility to social influence in phishing emails
Parsons, K., Butavicius, M., Delfabbro, P., & Lillie, M. (2019) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2019.02.007 · Cited by 135
Advancing Phishing Email Detection: A Comparative Study of Deep Learning Models
Altwaijry, Ν., Al-Turaiki, I. M., Alotaibi, R., & Alakeel, F. (2024) · Sensors · doi:10.3390/s24072077 · Cited by 135 · cited 1×
“…(HR et al., 2020), recurrent convolutional neural networks (RCNNs) (Fang et al., 2019), and other deep neural network architectures (Yerima and Alza-ylaee, 2020; Magdy et al., 2022; Rathee and Mann, 2022; Bagui et al., 2021; Sethi et al., 2022; Atawneh and Aljehani, 2023; Altwaijry et al., 2024).”
BackgroundThe design of phishing studies: Challenges for researchers
Parsons, K., McCormac, A., Pattinson, M., Butavicius, M., & Jerram, C. (2015) · Computers & Security · doi:10.1016/j.cose.2015.02.008 · Cited by 129 · cited 1×
“Therefore, organization normally train their employees to identify suspected phishing emails and avoid phishing scams (Parsons et al., 2015; Singh et al., 2019; Weaver et al., 2021).”
BackgroundDeep learning model for deep fake face recognition and detection
ST, S., Ayoobkhan, M. U. A., V, K. K., Bacanin, N., K, V., Štěpán, H., & Pavel, T. (2022) · PeerJ Computer Science · doi:10.7717/peerj-cs.881 · Cited by 128
High Accuracy Phishing Detection Based on Convolutional Neural Networks
Yerima, S. Y., & Alzaylaee, M. K. (2020) · International Conference on Computer Applications & Information Security (ICCAIS) · doi:10.1109/iccais48893.2020.9096869 · Cited by 127
Getting Started with Topic Modeling and MALLET
Graham, S., Weingart, S., & Milligan, I. (2012) · The Programming Historian · doi:10.46430/phen0017 · Cited by 119 · cited 10×
“As the figure shows, MALLET with Bayes Network classifier provided the best performance, but the differences between the algorithms are minor.”
MethodInfluentialDetecting Phishing Emails the Natural Language Way
Verma, R. M., Shashidhar, N. K., & Hossain, N. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33167-1_47 · Cited by 107
Persuasion: How phishing emails can influence users and bypass security measures
Ferreira, A., & Teles, S. (2019) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2018.12.004 · Cited by 99 · cited 1×
“It is therefore important for the attacker that the email messages are crafted by using social engineering aspects to optimize the chances of earning the trust of the potential victim (Butavicius et al., 2016; Ferreira and Teles, 2019; Wash, 2020; Singh et al., 2020).”
BackgroundEfficient spam and phishing emails filtering based on deep learning
Magdy, S., Abouelseoud, Y., & Mikhail, M. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.108826 · Cited by 94 · cited 1×
“…(HR et al., 2020), recurrent convolutional neural networks (RCNNs) (Fang et al., 2019), and other deep neural network architectures (Yerima and Alza-ylaee, 2020; Magdy et al., 2022; Rathee and Mann, 2022; Bagui et al., 2021; Sethi et al., 2022; Atawneh and Aljehani, 2023; Altwaijry et al., 2024).”
BackgroundMachine Learning and Deep Learning for Phishing Email Classification using One-Hot Encoding
Bagui, S. S., Nandi, D., Bagui, S., & White, R. J. (2021) · Journal of Computer Science · doi:10.3844/jcssp.2021.610.623 · Cited by 92 · cited 1×
“…(HR et al., 2020), recurrent convolutional neural networks (RCNNs) (Fang et al., 2019), and other deep neural network architectures (Yerima and Alza-ylaee, 2020; Magdy et al., 2022; Rathee and Mann, 2022; Bagui et al., 2021; Sethi et al., 2022; Atawneh and Aljehani, 2023; Altwaijry et al., 2024).”
BackgroundPhishing Email Detection Model Using Deep Learning
Atawneh, S., & Aljehani, H. (2023) · Electronics · doi:10.3390/electronics12204261 · Cited by 89 · cited 1×
“…(HR et al., 2020), recurrent convolutional neural networks (RCNNs) (Fang et al., 2019), and other deep neural network architectures (Yerima and Alza-ylaee, 2020; Magdy et al., 2022; Rathee and Mann, 2022; Bagui et al., 2021; Sethi et al., 2022; Atawneh and Aljehani, 2023; Altwaijry et al., 2024).”
BackgroundCopyright in generative deep learning
Franceschelli, G., & Musolesi, M. (2022) · Data & Policy · doi:10.1017/dap.2022.10 · Cited by 81 · cited 1×
“That is done by using copyrighted art for training generative AI systems, that consequently generate work heavily based on the copyrighted art it was trained with (Franceschelli and Musolesi, 2022; Samuelson, 2023).”
MethodDetection of phishing emails using data mining algorithms
Smadi, S., Aslam, N., Zhang, L., Alasem, R., & Hossain, M. A. (2015) · International Conference on Software, Knowledge, Information Management and Applications (SKIMA) · doi:10.1109/skima.2015.7399985 · Cited by 78 · cited 2×
“Existing solutions are based on Support Vector Machines (SVM) (Niu et al., 2017), J48 (Smadi et al., 2015), random forest (HR et al., 2020), recurrent convolutional neural networks (RCNNs) (Fang et al., 2019), and other deep neural network architectures (Yerima and Alza-ylaee, 2020; Magdy et al.,…”
MethodHow Experts Detect Phishing Scam Emails
Wash, R. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3415231 · Cited by 76 · cited 1×
“It is therefore important for the attacker that the email messages are crafted by using social engineering aspects to optimize the chances of earning the trust of the potential victim (Butavicius et al., 2016; Ferreira and Teles, 2019; Wash, 2020; Singh et al., 2020).”
BackgroundDevelopment of anti-phishing browser based on random forest and rule of extraction framework
R, M. G. H., Adithya, M. V., Gunesh Prasad, S., & Vinay, S. (2020) · Cybersecurity · doi:10.1186/s42400-020-00059-1 · Cited by 65 · cited 1×
“Existing solutions are based on Support Vector Machines (SVM) (Niu et al., 2017), J48 (Smadi et al., 2015), random forest (HR et al., 2020), recurrent convolutional neural networks (RCNNs) (Fang et al., 2019), and other deep neural network architectures (Yerima and Alza-ylaee, 2020; Magdy et al.,…”
MethodPhishing email strategies: Understanding cybercriminals' strategies of crafting phishing emails
Stojnic, T., Vatsalan, D., & Arachchilage, N. A. G. (2021) · Security and Privacy · doi:10.1002/spy2.165 · Cited by 63 · cited 1×
“A phishing email attack (Fette et al., 2007; Hong, 2012; Khonji et al., 2013; Almomani et al., 2013; Parsons et al., 2019; Patel et al., 2019; Stojnic et al., 2021; Do et al., 2022) is a form of cybersecurity attack in which the attacker contacts a potential victim through an email message that…”
BackgroundTraining to Detect Phishing Emails: Effects of the Frequency of Experienced Phishing Emails
Singh, K., Aggarwal, P., Rajivan, P., & González, C. (2019) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1071181319631355 · Cited by 51 · cited 1×
“Therefore, organization normally train their employees to identify suspected phishing emails and avoid phishing scams (Parsons et al., 2015; Singh et al., 2019; Weaver et al., 2021).”
BackgroundAn Evaluation of Naive Bayesian Anti-Spam Filtering Techniques
Deshpande, V. P., Erbacher, R. F., & Harris, C. (2007) · IEEE SMC Information Assurance Workshop (IAW) · doi:10.1109/iaw.2007.381951 · Cited by 49 · cited 1×
“3 https://www.cs.cmu.edu/ ~enron/ In addition to these datasets, we also used the Ling-Spam dataset (Sakkis et al., 2003; Deshpande et al., 2007) as a dataset of manually crafted regular and spam emails.”
MethodPhishing Emails Detection Using CS-SVM
Niu, W., Zhang, X., Yang, G., Ma, Z., & Zhuo, Z. (2017) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa/iucc.2017.00160 · Cited by 43 · cited 2×
“Existing solutions are based on Support Vector Machines (SVM) (Niu et al., 2017), J48 (Smadi et al., 2015), random forest (HR et al., 2020), recurrent convolutional neural networks (RCNNs) (Fang et al., 2019), and other deep neural network architectures (Yerima and Alza-ylaee, 2020; Magdy et al.,…”
MethodDetection of E-Mail Phishing Attacks – using Machine Learning and Deep Learning
Rathee, D., & Mann, S. (2022) · International Journal of Computer Applications · doi:10.5120/ijca2022921868 · Cited by 42 · cited 1×
“…(HR et al., 2020), recurrent convolutional neural networks (RCNNs) (Fang et al., 2019), and other deep neural network architectures (Yerima and Alza-ylaee, 2020; Magdy et al., 2022; Rathee and Mann, 2022; Bagui et al., 2021; Sethi et al., 2022; Atawneh and Aljehani, 2023; Altwaijry et al., 2024).”
BackgroundComparative Study of Classification Algorithms for Spam Email Detection
Sharaff, A., Nagwani, N. K., & Dhadse, A. (2015) · Springer eBooks · doi:10.1007/978-81-322-2553-9_23 · Cited by 41 · cited 1×
“Since released to the public, it has been a common dataset for the development and testing of machine learning methods for numerous tasks such as spam detection (Sharaff et al., 2016), categorization into folders (Bekkerman, 2004), network analysis (Hardin et al., 2015), and more.”
Network Analysis with the Enron Email Corpus
Hardin, J., Sarkis, G., & URC, P. C. (2015) · Journal of Statistics Education · doi:10.1080/10691898.2015.11889734 · Cited by 30 · cited 1×
“Since released to the public, it has been a common dataset for the development and testing of machine learning methods for numerous tasks such as spam detection (Sharaff et al., 2016), categorization into folders (Bekkerman, 2004), network analysis (Hardin et al., 2015), and more.”
Perceptual representation of spam and phishing emails
Patel, P. P., Sarno, D. M., Lewis, J., Shoss, M. K., Neider, M. B., & Bohil, C. J. (2019) · Applied Cognitive Psychology · doi:10.1002/acp.3594 · Cited by 25 · cited 1×
“A phishing email attack (Fette et al., 2007; Hong, 2012; Khonji et al., 2013; Almomani et al., 2013; Parsons et al., 2019; Patel et al., 2019; Stojnic et al., 2021; Do et al., 2022) is a form of cybersecurity attack in which the attacker contacts a potential victim through an email message that…”
BackgroundTraining Users to Identify Phishing Emails
Weaver, B. W., Braly, A. M., & Lane, D. M. (2021) · Journal of Educational Computing Research · doi:10.1177/0735633121992516 · Cited by 25 · cited 1×
“Therefore, organization normally train their employees to identify suspected phishing emails and avoid phishing scams (Parsons et al., 2015; Singh et al., 2019; Weaver et al., 2021).”
BackgroundWhat makes phishing emails hard for humans to detect?
Singh, K., Aggarwal, P., Rajivan, P., & González, C. (2020) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1071181320641097 · Cited by 21 · cited 1×
“It is therefore important for the attacker that the email messages are crafted by using social engineering aspects to optimize the chances of earning the trust of the potential victim (Butavicius et al., 2016; Ferreira and Teles, 2019; Wash, 2020; Singh et al., 2020).”
BackgroundJayatilaka, A., Arachchilage, N. A. G., & AliBabar, M. (2024) · Workshop on Usable Security (USEC) · doi:10.14722/usec.2024.23072 · Cited by 20
A data science approach to 138 years of congressional speeches
Tucker, E. C., Capps, C. J., & Shamir, L. (2020) · Heliyon · doi:10.1016/j.heliyon.2020.e04417 · Cited by 14 · cited 1×
“UDAT was developed for the purpose of digital hu-manities (Rosebaugh and Shamir, 2022; Swisher and Shamir, 2023), but can also be used as a general-purpose document classifier (Shamir, 2017; Tucker et al., 2020; Shamir, 2021).”
MethodSelf-citationSpam Email Detection Using Machine Learning and Neural Networks
Sethi, M., Chandra, S., Chaudhary, V., & Dahiya, Y. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-5157-1_22 · Cited by 12 · cited 1×
“…(HR et al., 2020), recurrent convolutional neural networks (RCNNs) (Fang et al., 2019), and other deep neural network architectures (Yerima and Alza-ylaee, 2020; Magdy et al., 2022; Rathee and Mann, 2022; Bagui et al., 2021; Sethi et al., 2022; Atawneh and Aljehani, 2023; Altwaijry et al., 2024).”
BackgroundDetection Technique and Mitigation Against a Phishing Attack
Fetooh, H. T. M., El-Gayar, M. M., & Aboelfetouh, A. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0120922 · Cited by 10 · cited 1×
“It has been shown that such attacks can also be detected at the level of the network packets (Fetooh et al., 2021).”
BackgroundActivity-centred Search in Email.
Minkov, E., Balasubramanyan, R., & Cohen, W. W. (2008) · Cited by 10
A data science and machine learning approach to continuous analysis of Shakespeare's plays
Swisher, C., & Shamir, L. (2023) · Journal of Data Mining & Digital Humanities · doi:10.46298/jdmdh.10829 · Cited by 9 · cited 1×
“UDAT was developed for the purpose of digital hu-manities (Rosebaugh and Shamir, 2022; Swisher and Shamir, 2023), but can also be used as a general-purpose document classifier (Shamir, 2017; Tucker et al., 2020; Shamir, 2021).”
MethodSelf-citationData Science Approach to Compare the Lyrics of Popular Music Artists
Rosebaugh, C., & Shamir, L. (2022) · Unisia · doi:10.20885/unisia.vol40.iss1.art1 · Cited by 8 · cited 1×
“UDAT was developed for the purpose of digital hu-manities (Rosebaugh and Shamir, 2022; Swisher and Shamir, 2023), but can also be used as a general-purpose document classifier (Shamir, 2017; Tucker et al., 2020; Shamir, 2021).”
MethodSelf-citationUDAT: Compound quantitative analysis of text using machine learning
Shamir, L. (2020) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqaa007 · Cited by 7 · cited 15×
“As described in (Shamir, 2021), the lemma diversity is determined by the number of different lemmata used in the text divided by the total number of lemmata in the text.”
BackgroundMethodInfluentialSelf-citationUDAT: A multi-purpose data analysis tool
Shamir, L. (2017) · Astrophysics Source Code Library · Cited by 6
Self-citationTech Services on the Web: MALLET-MAchine Learning for LanguagE Toolkit; http://mallet.cs.umass.edu/
Falk, P. K. (2014) · Technical Services Quarterly · doi:10.1080/07317131.2014.943038 · Cited by 4 · cited 1×
“MALLET is a general-purpose document classifier, and its ability to classify manually-generated spam emails has been demonstrated (Falk, 2014).”
BackgroundJayatilaka, A., Arachchilage, N. A. G., & Babar, M. A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.13199 · Cited by 3 · cited 1×
“Although such training can reduce the likelihood of a person to be deceived by a phishing email, attending such training still does not provide full guarantee that the trained person does not become a phishing scam victim (Jayatilaka et al., 2024).”
Background
Research works printed but not linked: 2
- Butavicius, M., Parsons, K., Pattinson, M., and McCormac, A. (2016). Breaching the human firewall: Social engineering in phishing and spear-phishing emails. arXiv.
- Diesner, J., and Carley, K.M. (2005, January 21–23). Exploration of communication networks from the Enron email corpus. Proceedings of the SIAM International Conference on Data Mining: Workshop on Link Analysis, Counterterrorism and Security, Newport Beach, CA, USA.
Cited by
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 671
“They are optimized to execute repeatable operations within a fixed domain, such as email filtering [67, 68], database querying [69], or calendar coordination [44,70].”
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · arXiv · doi:10.48550/arxiv.2505.10468 · Cited by 295
“They are optimized to execute repeatable operations within a fixed domain, such as email filtering [67, 68], database querying [69], or calendar coordination [44,70].”
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186
Alhuzali, A., Alloqmani, A., Aljabri, M., & Alharbi, F. (2025) · Applied Sciences · doi:10.3390/app15063396 · Cited by 97
“As cybercriminals leverage AI to enhance deception and evade detection, developing more advanced and adaptive security solutions is imperative to detect these evolving threats in real time [8].”
Jabir, R. M., Le, J., & Nguyen, C. (2025) · AI · doi:10.3390/ai6080174 · Cited by 84
Metadata
- Authors
- Eze, C. S., & Shamir, L.
- Affiliations
- Kansas State University (US)
- Corresponding author
- Shamir, Lior
- ORCID
- Shamir, Lior
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2024-05-09
- Volume
- 13
- Issue
- 10
- Pages
- 1839
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W4396760408
- Cited by
- 47
- References
- 55
- Citations by year
- 2026: 21 · 2025: 22 · 2024: 4
- FWCI
- 17.63
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- NSF (2148878)
- Topics
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Authorship Attribution and Profiling
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Keywords
- generative AI, email corpus, phishing detection, machine learning classification, cybersecurity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.