Sanmeet Kaur

Improving detection rate using misuse detection and machine learning

Network security is the provision made in an underlying computer network or rules made by the administrator to protect the network and its resources from unauthorized access. Network Security is becoming a crucial issue for all the firms and companies and with the increase in knowledge of intruders and hackers they have made many prosperous attempts to bring down web services and high-profile company networks. Misuse detection detects intrusions by matching the network traffic with a database of stored signatures and anomaly detection looks for behavior deviating from normal or common behavior for detecting intrusions. The primary objective of this paper is to combine both these techniques. The KDD dataset is used for this purpose. Finally, the data is processed by classification algorithms to obtain the results. The results show a high percentage of correct classification and accuracy. Experimental evaluation shows that the combined approach of Machine learning and misuse detection gives better performance.

Antispammer for Mobile Messages

SMS spams are dramatically increasing year by year due to the growth of mobile phone users around the world. Recent reports have clearly indicated the same. Mobile or SMS spam is a physical and thriving problem due to the fact that bulk pre-pay SMS packages are conveniently available these days and SMS is considered as a trusted and personal service, so it gathers more response rate from the customers. SMS spam filtering is a comparatively recent errand to deal such a problem. It inherits many concerns and quick fixes from Email spam filtering. However it fronts its own certain issues and problems. This paper inspires to work on the task of filtering mobile messages as Ham or Spam. The paper analyses different machine learning classifiers on large corpus of SMS spam.

SMS spam detection for Indian messages

The growth of the mobile phone users has led to a dramatic increase in SMS spam messages. Though in most parts of the world, mobile messaging channel is currently regarded as “clean” and trusted, on the contrast recent reports clearly indicate that the volume of mobile phone spam is dramatically increasing year by year. It is an evolving setback especially in the Middle East and Asia. SMS spam filtering is a comparatively recent errand to deal such a problem. It inherits many concerns and quick fixes from Email spam filtering. However it fronts its own certain issues and problems. This paper inspires to work on the task of filtering mobile messages as Ham or Spam for the Indian Users by adding Indian messages to the worldwide available SMS dataset. The paper analyses different machine learning classifiers on large corpus of SMS messages for Indian people.

A proactive framework for automatic detection of zero-day HTTP attacks on educational institutions

Education plays a vital role in economic development and improvements in human welfare. The education sector has changed a lot over the years, and Information and Communication Technology (ICT) plays an important role in the education sector. Almost every activity in universities and colleges, right from the procedure of counselling to admission and fee deposits, has been automated. Attendance records, quizzes, evaluations, marks and grade submission also involve use of ICT. Email, distance learning and other services that extend education beyond the campus are potentially significant. With the increased use of Information and Communication Technology (ICT) in educational institutes, security has become a big area of concern. Current signature-based intrusion detection provides only limited protection. Sanmeet Kaur and Maninder Singh of Thapar University, Patiala, India, propose a new hybrid automated signature generation system that is able to detect cross-site scripting, directory traversal, command injection and SQL injection attacks.