Diverse Datasets and a Customizable Benchmarking Framework for Phishing

Zeng, Victor; Baki, Shahryar; Aassal, Ayman El; Verma, Rakesh M.; Moraes, Luis F. T.; Das, Avisha

doi:10.1145/3375708.3380313

Cited by 17 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several recent studies are similar to the research carried out by Priya et al [25], Indrasiri et al [26], Ozcan et al [27], Bu & Kim [28], Zeng et al [29], and el Aassal et al [17], which evaluated the performance of classification techniques and their impact on various datasets. However, these were limited to phishing websites, in contrast to this research, which involved email and website phishing.…”

Section: Related Worksupporting

confidence: 58%

Performance Evaluation of Phishing Classification Techniques on Various Data Sources and Schemes

et al. 2023

View full text Add to dashboard Cite

Phishing attacks have become a perilous threat in recent years, which has led to numerous studies to determine the classification technique that best detects these attacks. Several studies have made comparisons using only specific datasets and techniques without including the most crucial aspect, which is the performance evaluation of data changes. Hence, classification techniques cannot be generalized if they only use specific datasets and techniques. Therefore, this research determined the performance of classification techniques on changing data through a subset of schemes in a dataset. It was conducted using unbalanced and balanced phishing datasets, as well as subset schemes in ratios of 90:10, 80:20, 70:30, and 60:40. The thirteen most recent classification techniques used in preliminary phishing studies were compared and evaluated against ten performance measures. The results showed that the proposed schemes successfully uncover the maximum and minimum performance obtained by a classification technique. These comparisons can provide deeper insights into phishing classification techniques than related research.

show abstract

Section: Related Worksupporting

confidence: 58%

Performance Evaluation of Phishing Classification Techniques on Various Data Sources and Schemes

et al. 2023

View full text Add to dashboard Cite

show abstract

“…It mainly affects the solution's performance, and the solution needs to be retrained occasionally to retain its performance [38]. However, retraining is again a challenge in the anti-phishing domain, as collecting a considerable amount of labelled phishing data is difficult in the current context [42], [53]. Furthermore, adversarial attacks are also considered a threat to machine learning-based anti-phishing solutions [42].…”

Section: ) Machine Learning-based Phishing Detectionmentioning

confidence: 99%

“…Further, PhishDet has used adam optimiser with a categorical crossentropy loss function to have the least difference between actual and predicted outputs. A. DATASETS Generally, phishing websites exist only for a limited time on the web [53]. Therefore, it is not easy to construct more reliable datasets for a study if the study depends on URL and HTML content like the current study.…”

Section: Phishdetmentioning

confidence: 99%

“…Therefore, it is not easy to construct more reliable datasets for a study if the study depends on URL and HTML content like the current study. However, in previous studies, PhishTank, OpenPhish and APWG were mainly used when constructing phishing datasets, and legitimates were generated mainly through Alexa [53]. Although these sources exist to construct a dataset for a study, a diverse and extensive dataset is the key to accurate and unbiased detection [38].…”

Section: Phishdetmentioning

confidence: 99%

See 1 more Smart Citation

Combining Long-Term Recurrent Convolutional and Graph Convolutional Networks to Detect Phishing Sites Using URL and HTML

Ariyadasa

Fernando

2022

IEEE Access

View full text Add to dashboard Cite

Phishing, a well-known cyber-attack practice has gained significant research attention in the cyber-security domain for the last two decades due to its dynamic attacking strategies. Although different solutions have been exercised against phishing, phishing attacks have dramatically increased in the past few years. Recent studies have shown that machine learning has become prominent in the present antiphishing context, and the techniques like deep learning have extensively improved anti-phishing tools' detection ability. This paper proposes PhishDet, a new way of detecting phishing websites through Longterm Recurrent Convolutional Network and Graph Convolutional Network using URL and HTML features. PhishDet is the first of its kind, which uses the powerful analysis and processing capabilities of Graph Neural Network in the anti-phishing domain and recorded 96.42% detection accuracy, with a 0.036 false-negative rate. It is effective against zero-day attacks, and the average detection time which is 1.8 seconds could also be considered realistic. The feature selection of PhishDet is automatic and occurs inside the system, as PhishDet gradually learns URLs and HTML content features to handle constantly changing phishing attacks. This has outperformed similar solutions by achieving a 99.53% f1-score with a public benchmark dataset. However, PhishDet requires periodic retraining to maintain its performance over time. If such retraining could be facilitated, PhishDet could fight against phishers for a more extended period to safeguard Internet users from this Internet threat.

show abstract

“…It is a new dataset with two version available IWSPA v1 [102] and IWSPA v2 [103] [S87] IWSPA-AP [104], [105] Collects and maintain phishing URL data on the internet. S47, S53, S58, [93] S40, S69, S71], S75, S77, S88] OpenPhish [96] Provide an active collection of phishing website URLs [S28, S46, S53, S88] Anti-Phishing Alliance Provides a list of phishing websites in china.…”

Section: Enron Emailmentioning

confidence: 99%

Machine Learning for Detecting Data Exfiltration: A Review

Sabir,

Ullah,

Babar

et al. 2020

Preprint

View full text Add to dashboard Cite

Research at the intersection of cybersecurity, Machine Learning (ML), and Software Engineering (SE) has recently taken significant steps in proposing countermeasures for detecting sophisticated data exfiltration attacks. It is important to systematically review and synthesize the ML-based data exfiltration countermeasures for building a body of knowledge on this important topic. Objective: This paper aims at systematically reviewing ML-based data exfiltration countermeasures to identify and classify ML approaches, feature engineering techniques, evaluation datasets, and performance metrics used for these countermeasures. This review also aims at identifying gaps in research on ML-based data exfiltration countermeasures. Method: We used Systematic Literature Review (SLR) method to select and review 92 papers. Results: The review has enabled us to (a) classify the ML approaches used in the countermeasures into data-driven, and behaviour-driven approaches, (b) categorize features into six types: behavioral, content-based, statistical, syntactical, spatial and temporal, (c) classify the evaluation datasets into simulated, synthesized, and real datasets and (d) identify 11 performance measures used by these studies. Conclusion: We conclude that: (i) the integration of data-driven and behaviour-driven approaches should be explored; (ii) There is a need of developing high quality and large size evaluation datasets; (iii) Incremental ML model training should be incorporated in countermeasures; (iv) resilience to adversarial learning should be considered and explored during the development of countermeasures to avoid poisoning attacks; and (v) the use of automated feature engineering should be encouraged for efficiently detecting data exfiltration attacks.

show abstract

Diverse Datasets and a Customizable Benchmarking Framework for Phishing

Cited by 17 publications

References 13 publications

Performance Evaluation of Phishing Classification Techniques on Various Data Sources and Schemes

Performance Evaluation of Phishing Classification Techniques on Various Data Sources and Schemes

Combining Long-Term Recurrent Convolutional and Graph Convolutional Networks to Detect Phishing Sites Using URL and HTML

Machine Learning for Detecting Data Exfiltration: A Review

Contact Info

Product

Resources

About