Web document clustering: a feasibility demonstration
Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval
Optimal suffix tree construction with large alphabets
FOCS '97 Proceedings of the 38th Annual Symposium on Foundations of Computer Science
A comparison of machine learning techniques for phishing detection
Proceedings of the anti-phishing working groups 2nd annual eCrime researchers summit
Linear pattern matching algorithms
SWAT '73 Proceedings of the 14th Annual Symposium on Switching and Automata Theory (swat 1973)
| Hi-index | 0.00 |
Phishing websites gain billions of dollars of profits from stealing personal identities and private data. In this paper, an URL classification method is proposed to prioritize suspicious URLs in terms of phishing websites by examining the URL structures and performing string classification. Due to the fact that the average uptime of phishing sites is short, it is important for the proposed method to `timely react' to the newest phishing URLs while the URLs are still valid. Since the proposed method does not involve any web-crawling or content analysis, it can generate prioritized signatures from phishing URLs in a real-time fashion. Moreover, the proposed method consumes very little computing resources that, with an additional moderate PC, it can be injected into any existing real-time URL analysis system.