Visual Similarity-Based Phishing Detection Scheme Using Image and CSS with Target Website Finder

Haruta, Shuichiro; Asahina, Hiromu; Sasase, Iwao

doi:10.1109/glocom.2017.8254506

Cited by 17 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A phishing website detection method has been proposed by Haruta et al., 9 and they combined visual similarity from the website CSS and website image. For the image-based similarity, wavelet decomposition was first applied to extract a descriptor, and minHash method is used to calculate the similarity score.…”

Section: Literature Reviewmentioning

confidence: 99%

Visual similarity-based phishing detection using deep learning

Saeed

2022

J. Electron. Imag.

View full text Add to dashboard Cite

Phishing is a common cybercrime that tempts a target to reveal personal and financial information by imitating a legitimate webpage. Classical techniques, such as list-based, and heuristic approaches have focused on identifying the uniform resource locator (URL). However, cybercriminals have uncovered several methods to evade URL-based techniques. Recently, researchers have started developing techniques that are based on visual similarity to detect phishing webpages. However, using visual similarity raises several computer vision-related issues such as webpage segmentation and feature extraction. Deep learning provides a suitable solution to these issues as it integrates feature extraction, feature selection, and classification in an end-toend system. We have made the first attempt to detect phishing webpages based on visual similarity by modifying and retraining deep neural networks. A comprehensive evaluation on two publicly available databases has shown a marked improvement of around 7% classification accuracy.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Visual similarity-based phishing detection using deep learning

Saeed

2022

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

“…Haruta et al [10] proposed the use of an image similarity analysis for phishing detection. Their method combines an image similarity analysis and the CSS format to identify legitimate websites and phishing websites.…”

Section: Visual Similarity Analysismentioning

confidence: 99%

“…In this study, we collected 24471 phishing sites from PhishTank in the collection model, with 3850 legitimate sites retrieved from the target column of the corresponding is ip address f 16 script block rate f 3 dots f 17 style block rate f 4 is special words f 18 get title feature f 5 url linkin num f 19 is login form f 6 url traffic rank f 20 is with whois f 7 get kbytes f 21 get time f 8 is frame f 22 is redirect f 9 is meta redirect f 23 ipv4 numbers f 10 is meta base64 redirect f 24 ipv6 numbers f 11 same extern domain script rate f 25 organization f 12 same external domain link rate f 26 is alias f 13 same external domain img rate f 27 is weird serial f 14 external a tag same domain f 28 get day age phishing sites. Basically, the number of phishing sites was considerably larger than the number of legitimate sites, because hackers usually imitate a specific legitimate site and design multiple similar phishing sites.…”

Section: Training Datasetmentioning

confidence: 99%

See 1 more Smart Citation

AI@ntiPhish — Machine Learning Mechanisms for Cyber-Phishing Attack

Chen

2019

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

This study proposes a novel machine learning architecture and various learning algorithms to build-in anti-phishing services for avoiding cyber-phishing attack. For the rapid develop of information technology, hackers engage in cyber-phishing attack to steal important personal information, which draws information security concerns. The prevention of phishing website involves in various aspect, for example, user training, public awareness, fraudulent phishing, etc. However, recent phishing research has mainly focused on preventing fraudulent phishing and relied on manual identification that is inefficient for real-time detection systems. In this study, we used methods such as ANOVA, X 2 , and information gain to evaluate features. Then, we filtered out the unrelated features and obtained the top 28 most related features as the features to use for the training and evaluation of traditional machine learning algorithms, such as Support Vector Machine (SVM) with linear or rbf kernels, Logistic Regression (LR), Decision tree, and K-Nearest Neighbor (KNN). This research also evaluated the above algorithms with the ensemble learning concept by combining multiple classifiers, such as Adaboost, bagging, and voting. Finally, the eXtreme Gradient Boosting (XGBoost) model exhibited the best performance of 99.2%, among the algorithms considered in this study. key words: anti-phishing, machine learning algorithm, ensemble learning mechanism, cyber attack

show abstract

“…Traditional phishing scams detection methods cannot be well adapted to the Ethereum scenario. As Figure 1 shows, traditional phishing scams rely on building forged platforms (websites or software) to collect sensitive information or receive remittances from victims, so traditional methods focus on mining forged platform patterns, such as CSS styles [13], website URLs [23], etc. However, in Ethereum, phishing organizations take high-reward propaganda to induce remittances[6], they can swindle money directly without forged platforms by spreading phishing addresses to victims in any way such as emails, chat groups, etc.…”

Section: Introductionmentioning

confidence: 99%

TTAGN: Temporal Transaction Aggregation Graph Network for Ethereum Phishing Scams Detection

Gou

Liu

et al. 2022

Proceedings of the ACM Web Conference 2022

View full text Add to dashboard Cite

In recent years, phishing scams have become the most serious type of crime involved in Ethereum, the second-largest blockchain platform. The existing phishing scams detection technology on Ethereum mostly uses traditional machine learning or network representation learning to mine the key information from the transaction network to identify phishing addresses. However, these methods adopt the last transaction record or even completely ignore these records, and only manual-designed features are taken for the node representation. In this paper, we propose a Temporal Transaction Aggregation Graph Network (TTAGN) to enhance phishing scams detection performance on Ethereum. Specifically, in the temporal edges representation module, we model the temporal relationship of historical transaction records between nodes to construct the edge representation of the Ethereum transaction network. Moreover, the edge representations around the node are aggregated to fuse topological interactive relationships into its representation, also named as trading features, in the edge2node module. We further combine trading features with common statistical and structural features obtained by graph neural networks to identify phishing addresses. Evaluated on real-world Ethereum phishing scams datasets, our TTAGN (92.8% AUC, and 81.6% F1score) outperforms the state-of-the-art methods, and the effectiveness of temporal edges representation and edge2node module is also demonstrated. CCS CONCEPTS• Applied computing → Digital cash; • Security and privacy → Phishing.

show abstract

Visual Similarity-Based Phishing Detection Scheme Using Image and CSS with Target Website Finder

Cited by 17 publications

References 6 publications

Visual similarity-based phishing detection using deep learning

Visual similarity-based phishing detection using deep learning

AI@ntiPhish — Machine Learning Mechanisms for Cyber-Phishing Attack

TTAGN: Temporal Transaction Aggregation Graph Network for Ethereum Phishing Scams Detection

Contact Info

Product

Resources

About