Malay Language Phishing Email Collection

A balanced dataset of 6,200 Malay emails annotated for phishing detection. The dataset is specifically designed for training models to identify phishing attempts in the Malay language. The author and specific collection time range are not provided.

Use Cases

• Train a binary classifier to predict phishing intent using the email body text.
• Analyze linguistic patterns and keywords specific to Malay phishing attempts within the email content.
• Benchmark multilingual phishing detection models using the labeled Malay email corpus.
• Develop feature extraction techniques for phishing detection based on email text features.

Strengths

• Contains 6,200 email samples.
• Described as a balanced dataset, suggesting an even class distribution for phishing and non-phishing labels.

Limitations

• The specific number of rows and columns is unknown.
• No information on the annotation methodology or label quality is available.
• The temporal and geographic scope of the email collection is unspecified.

Provenance

Source

Kaggle