Chinese Spam Detection Using a Hybrid BiGRU-CNN Network with Joint Textual and Phonetic Embedding

Yao, Jinliang; Wang, Chenrui; Hu, Chuang; Huang, Xiucheng

doi:10.3390/electronics11152418

Cited by 6 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Phishing emails frequently exhibit linguistic inconsistencies, such as misspellings, grammar errors, and unnatural language usage. Studies by [10] and [11] have explored the linguistic features that are indicative of phishing. These features include grammatical errors, unusual syntax, and inconsistent language usage, which are often present in phishing emails.…”

Section: I) Linguistic Cues and Stylistic Anomaliesmentioning

confidence: 99%

Sentence Level Analysis Model for Phishing Detection Using KNN

Sawe,

Gikandi,

Kamau

et al. 2024

Journal of Cyber Security

View full text Add to dashboard Cite

Phishing emails have experienced a rapid surge in cyber threats globally, especially following the emergence of the COVID-19 pandemic. This form of attack has led to substantial financial losses for numerous organizations. Although various models have been constructed to differentiate legitimate emails from phishing attempts, attackers continuously employ novel strategies to manipulate their targets into falling victim to their schemes. This form of attack has led to substantial financial losses for numerous organizations. While efforts are ongoing to create phishing detection models, their current level of accuracy and speed in identifying phishing emails is less than satisfactory. Additionally, there has been a concerning rise in the frequency of phished emails recently. Consequently, there is a pressing need for more efficient and high-performing phishing detection models to mitigate the adverse impact of such fraudulent messages. In the context of this research, a comprehensive analysis is conducted on both components of an email message-namely, the email header and body. Sentence-level characteristics are extracted and leveraged in the construction of a new phishing detection model. This model utilizes K Nearest Neighbor (KNN) introducing the novel dimension of sentence-level analysis. Established datasets from Kaggle were employed to train and validate the model. The evaluation of this model's effectiveness relies on key performance metrics including accuracy of 0.97, precision, recall, and F1-measure.

show abstract

Section: I) Linguistic Cues and Stylistic Anomaliesmentioning

confidence: 99%

Sentence Level Analysis Model for Phishing Detection Using KNN

Sawe,

Gikandi,

Kamau

et al. 2024

Journal of Cyber Security

View full text Add to dashboard Cite

show abstract

“…Fu Biehe [12] integrated a bad text classifier based on key information reduction, a bad text classifier based on improved KNN, and a bad text classifier based on sensitive decision tree through Bagging to recognize bad text containing variant words. Yao J [13] et al used a BiGRU-CNN hybrid network with word-phonetic co-embedding to recognize spam emails containing variant words. spam emails containing homophones.…”

Section: Introductionmentioning

confidence: 99%

Variant bad text recognition based on ChineseBERT-BiGRU

Huawei,

Wei,

Fangjie

et al. 2024

Fourth International Conference on Machine Learning and Computer Application (ICMLCA 2023)

View full text Add to dashboard Cite

The bad text containing variant words seriously harms the health of the network environment. The existing methods for the recognition of bad variant text do not take into account the importance of the phonetic and positional information for the recognition of bad variant text. In this paper, a ChineseBERT-BiGRU variant bad text recognition model is proposed. This model first learns and trains the word vector of the text by inputting the pinyin information, font information and character information of the text, and then combines the position information of the text. Then the word vector of the text is input into BiGRU to learn richer semantic information of the text. Finally, the bad text containing variant words is identified through Softmax classification. The accuracy, accuracy and F1 values of ChineseBERT-BiGRU in the data set in this paper are compared with those of other models.

show abstract

“…The advent of smartphones with enhance features has contributed to huge adoption of short messaging by users due to its portability, mobility, ubiquity of services and its low cost continues to promote SMSM to become the most used means of communication globally. , Short Message Service (SMS) is text service in mobile communications with protocols that allow exchange of short text messages between fixed line or mobile phone devices (Ojugo & Ekurume, 2021aYao et al, 2022) Omede & Okpeki, 2023;Sahmoud & Mikki, 2022). An estimated 23-billion SMS was sent daily in 2014 globally; While, a total 8.3-trillion SMS was sent worldwide in the same year with net market revenue of over $128Billion in 2011.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Genetic Algorithm Trained Bayesian Ensemble for Short Messages Spam Detection

Odiakaose,

Emordi,

Ejeh

et al. 2024

AIMS Research Journal

View full text Add to dashboard Cite

Today’s popularity of the short messages services (SMS) has created a propitious environment for spamming to thrive. Spams are unsolicited advertising, adult-themed or inappropriate content, premium fraud, smishing and malware. They are a constant reminder of the need for an effective spam filter. However, SMS limitations of 160-charcaters and 140-bytes size as well as its being rippled with slangs, emoticons and abbreviations further inhibits effective training of models to aid accurate classification. The study proposes Genetic Algorithm Trained Bayesian Network solution that seeks to normalize noisy feats, expand text via use of lexicographic and semantic dictionaries that uses word sense disambiguation technique to train the underlying learning heuristics. And in turn, effectively help to classify SMS in spam and legitimate classes. Hybrid model comprises of text preprocessing, feature selection as well as training and classification section. Study uses a hybrid Genetic Algorithm trained Bayesian model for which the GA is used for feature selection; while, the Bayesian algorithm is used as classifier. Keywords: Hybrid Genetic Algorithm, Trained Bayesian Ensemble, Short Messages Spam Detection Odiakaose, C. Emordi, F. Ejeh, P., Ashioba, N., Odeh, C., Attoh, O. & Azaka, M. (2024): Hybrid Genetic Algorithm Trained Bayesian Ensemble for Short Messages Spam Detection. Journal of Advances in Mathematical & Computational Science. Vol. 12, No. 1. Pp 37-52. Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V12N1P4

show abstract

Chinese Spam Detection Using a Hybrid BiGRU-CNN Network with Joint Textual and Phonetic Embedding

Cited by 6 publications

References 40 publications

Sentence Level Analysis Model for Phishing Detection Using KNN

Sentence Level Analysis Model for Phishing Detection Using KNN

Variant bad text recognition based on ChineseBERT-BiGRU

Hybrid Genetic Algorithm Trained Bayesian Ensemble for Short Messages Spam Detection

Contact Info

Product

Resources

About