Universal Spam Detection using Transfer Learning of BERT Model

Tida, Vijay Srinivas; Hsu, Sonya

doi:10.48550/arxiv.2202.03480

Cited by 6 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, DL has also been leveraged for spam detection. A modified Transformer was employed for this purpose in [46], while a fine-tuned version of BERT was applied in [47,48].…”

Section: Spam Detectionmentioning

confidence: 99%

Development of an Automated Moderator for Deliberative Events

Bonechi

2024

Electronics

View full text Add to dashboard Cite

Online communication platforms have revolutionized interpersonal interactions by transcending geographical barriers. While facilitating connectivity, these platforms have introduced challenges such as overcoming linguistic differences and preventing spam and offensive content diffusion. This is particularly pertinent in the context of deliberative events, where online platforms could be used to extend the inclusion of citizens in democratic decision-making. In traditional deliberative events, human moderators and translators were used to facilitate conversation; however, the need for these figures imposed a limit on both the number of deliberative events that could be organized and the number of participants. In response, this paper proposes an automated moderator for deliberative events. The moderator is developed in Python for the online communication platform Discord and can be used, thanks to the integrated AI (Artificial Intelligence) tools, to automatically manage conversation agendas, prevent spam and inappropriate language, analyze the sentiment of the conversation, and translate messages into multiple languages. In particular, three classifiers, based on a pre-trained BERT (Bidirection Encoder Representations from Transformers), were fine-tuned for spam detection, toxic comments classification, and sentiment analysis. These allow the moderator to automatically detect and remove spam and offensive messages in different languages, send warnings to users, alert administrators, and, after repeated warnings, impose bans. Additionally, a built-in translator, based on Meta’s No Language Left Behind NLLB model, translates messages into five languages (Italian, English, French, German, and Polish). The developed bot was tested in a simulated deliberative event on a Discord server, demonstrating its ability to manage conversations and prevent linguistic abuse.

show abstract

“…More recently, DL has also been leveraged for spam detection. A modified Transformer was employed for this purpose in [46], while a fine-tuned version of BERT was applied in [47,48].…”

Section: Spam Detectionmentioning

confidence: 99%

Development of an Automated Moderator for Deliberative Events

Bonechi

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…In [54], Tida and Hsu used pre-trained Google's Bidirectional Encoder Representations from Transformers base uncased models to classify ham or spam emails in real-time situations -97% total accuracy was attained with an F1 score of 0.96. This study focused on training and testing using spam and ham emails/messages datasets.…”

Section: B Spam Detectionmentioning

confidence: 99%

A URL-Based Social Semantic Attacks Detection With Character-Aware Language Model

Almousa

Anwar

2023

IEEE Access

View full text Add to dashboard Cite

Social engineering attacks rely on human errors and behavioral choices. The semantic attack, a subcategory of social engineering attacks, utilizes behavioral or cosmetic deception vectors (e.g., attacker creates a malicious website that looks like and behaves like the legitimate one). The most common types of social semantic attacks include phishing, spamming, defacement, and malware attacks. We investigate the feasibility of developing URL-based social semantic attack detection models utilizing character-aware language models. Specifically, we developed three types of models: long short-term memory (LSTM)-based detection model, convolutional neural network (CNN)-based detection model, and CharacterBERT-based detection model. We benchmarked performances of different models for different attacks. Using the characterBERT-based detection model, the overall evaluation recorded a high detection accuracy of 99.65% by averaging the results of performing a 5-fold cross-validation. Considering the model performance per class, the CharacterBERT model ranked the best model among our 3 models in detecting the social semantic attacks, reaching best accuracy of 99.90% in detecting defacement attack.

show abstract

“…In. Tida et al [14] we have the evidence of BERT model being used again for email spam detection where there is use of four dataset where the spam percentage is ranging from 50% to 20%. Here the model is trained on [15] Wikipedia's unlabelled text corpus (2.5 million words) and book corpus (800 million words).So, we understand that there is extensive study has been performed to detect spam e-mails from ham emails [16].…”

Section: Literature Reviewmentioning

confidence: 99%

Spam Detection using Reference Text: A Preliminary Study for Spam Ground Truth Generation

Tarafdar,

Halder,

Dash

2023

Preprint

View full text Add to dashboard Cite

Spam detection is a large area of study that has been approached from many different angles. Spam has been a threat to the normal operation of the internet since the late 1990s and most recently. Today, spam is not just found in emails; it also affects several other platforms, including social media and chat web platforms. In recent years, there have been significant changes in both the variety and meaning of spam. We are throwing light on the topic of word spam in digital photographs distributed through an online chat platform in this paper. In this article, we’ll talk about spam texts as well as how to spot them.

show abstract

Universal Spam Detection using Transfer Learning of BERT Model

Cited by 6 publications

References 0 publications

Development of an Automated Moderator for Deliberative Events

Development of an Automated Moderator for Deliberative Events

A URL-Based Social Semantic Attacks Detection With Character-Aware Language Model

Spam Detection using Reference Text: A Preliminary Study for Spam Ground Truth Generation

Contact Info

Product

Resources

About