Microsoft technology licensing, llc (20240297900). PHISHING URL DETECTION USING TRANSFORMERS simplified abstract
Contents
PHISHING URL DETECTION USING TRANSFORMERS
Organization Name
microsoft technology licensing, llc
Inventor(s)
Jack Wilson Stokes Iii of North Bend WA (US)
Pranav Ravindra Maneriker of Columbus OH (US)
Arunkumar Gururajan of Sammamish WA (US)
Diana Anca Carutasu of Bellevue WA (US)
Edir Vinicio Garcia Lazo of Seattle WA (US)
PHISHING URL DETECTION USING TRANSFORMERS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240297900 titled 'PHISHING URL DETECTION USING TRANSFORMERS
The technology described in this patent application can identify phishing URLs using transformers. It tokenizes useful features from the subject URL, such as the text of the URL and other associated data like certificate data, referrer URL, and IP address. By building a joint byte pair encoding for these features and processing it through a transformer, the technology generates a transformer output, which is then input to a classifier to determine if the URL is a phishing URL. Additional training data can be generated by permuting token order, simulating homoglyph attacks, and simulating compound word attacks.
- Identifies phishing URLs using transformers
- Tokenizes useful features from subject URLs
- Includes text of the URL and associated data like certificate information, referrer URL, and IP address
- Builds a joint byte pair encoding for features
- Processes encoding through a transformer to generate a transformer output
- Input transformer output to a classifier to determine phishing URLs
- Generates additional training data by permuting token order and simulating attacks
Potential Applications: - Cybersecurity - Fraud detection - Phishing prevention tools
Problems Solved: - Identification of phishing URLs - Enhancing cybersecurity measures
Benefits: - Improved detection of phishing URLs - Enhanced security for users - Prevention of fraudulent activities
Commercial Applications: Title: Advanced Phishing Detection Technology This technology can be used in cybersecurity software, web browsers, and email clients to enhance security measures and protect users from phishing attacks. It has implications for financial institutions, e-commerce platforms, and any organization dealing with sensitive data.
Questions about Phishing URL Detection: 1. How does this technology improve upon existing methods of identifying phishing URLs?
This technology utilizes transformers and tokenizes useful features from URLs to enhance phishing detection accuracy.
2. What are the potential limitations of using transformers for phishing URL detection?
Transformers may require significant computational resources, and there could be challenges in scaling the technology for large-scale applications.
Original Abstract Submitted
the technology described herein can identify phishing urls using transformers. the technology tokenizes useful features from the subject url. the useful features can include the text of the url and other data associated with the url, such as certificate data for the subject url, a referrer url, an ip address, etc. the technology may build a joint byte pair encoding for the features. the token encoding may be processed through a transformer, resulting in a transformer output. the transformer output, which may be described as a token embedding, may be input to a classifier to determine whether the url is a phishing url. additional or improved url training data may be generated by permuting token order, by simulating a homoglyph attack, and by simulating a compound word attack.
