BIRESWAR BANIK - Academia.edu (original) (raw)
Uploads
Papers by BIRESWAR BANIK
Communications in Computer and Information Science
Phishing is an illegitimate method to collect secret information of any person or organization. I... more Phishing is an illegitimate method to collect secret information of any person or organization. Information like debit card, credit card details, PIN no, OTP, passwords, etc. are stolen by the attackers through phishing sites. Researchers have used different techniques to detect those phishing sites. But it is difficult to stay on a particular technique as attackers come with new tactics. In this paper, phishing and legitimate URL classifications are performed based on the lexical features of URLs. Feature selection technique is used to select the relevant features only. Accuracy for all combination of features with different numbers of features each time was evaluated to find the best possible combination of features. Performances are analyzed for different datasets with various parameters using four different machine learning techniques.
International Journal of Electronics and Applied Research, 2018
Phishing activities on the Internet are increasing day by day. It is an illicit attempt made by t... more Phishing activities on the Internet are increasing day by day. It is an illicit attempt made by the attackers to steal personal information such as bank account details, login id, passwords etc. Many of the researchers proposed to detect phishing URLs by extracting features from the content of the web pages. But lots of time and space is required for this. This paper presents an approach to detect phishing URLs in an efficient way based on URL features only. For detecting the phishing URLs SVM classifier is used. The performances are evaluated for different size of datasets using different number of features. The results are compared with other machine learning classification techniques. The proposed system is able to detect phishing websites using URL features only with accuracy of 96.35%.
Communications in Computer and Information Science
Phishing is an illegitimate method to collect secret information of any person or organization. I... more Phishing is an illegitimate method to collect secret information of any person or organization. Information like debit card, credit card details, PIN no, OTP, passwords, etc. are stolen by the attackers through phishing sites. Researchers have used different techniques to detect those phishing sites. But it is difficult to stay on a particular technique as attackers come with new tactics. In this paper, phishing and legitimate URL classifications are performed based on the lexical features of URLs. Feature selection technique is used to select the relevant features only. Accuracy for all combination of features with different numbers of features each time was evaluated to find the best possible combination of features. Performances are analyzed for different datasets with various parameters using four different machine learning techniques.
International Journal of Electronics and Applied Research, 2018
Phishing activities on the Internet are increasing day by day. It is an illicit attempt made by t... more Phishing activities on the Internet are increasing day by day. It is an illicit attempt made by the attackers to steal personal information such as bank account details, login id, passwords etc. Many of the researchers proposed to detect phishing URLs by extracting features from the content of the web pages. But lots of time and space is required for this. This paper presents an approach to detect phishing URLs in an efficient way based on URL features only. For detecting the phishing URLs SVM classifier is used. The performances are evaluated for different size of datasets using different number of features. The results are compared with other machine learning classification techniques. The proposed system is able to detect phishing websites using URL features only with accuracy of 96.35%.