Noor Ahmed Shaikh

Towards an automated multiagent system to monitor user activities against insider threat

The major problems faced by the networks are the hurdles generated by the native users. Survey has proved that the professional security measures are mainly focusing outside threats instead of the insiders. The traditional insider threat protection models do not work efficiently. There is need of an autonomous, robust and flexible model against insider threat. This paper presents an Agent-based User- Profiling model that monitors behaviour of the authorized users in an organization to avoid the risk. The profiling agents in the model record all actions of the authorized user and present all recorded behaviour to the manager agent for further processing. The manager agent creates and updates profiles of the enterprise users to monitor the behaviour so that the threat may be avoided, detected or recovered.

Segmentation of Arabic Text into Characters for Recognition

One of the steps of character recognition systems is the segmentation of words/sub-words into characters. The segmentation of text written in any Arabic script is a most difficult task. Due to this difficulty, many systems consider sub-words instead of a character as the basic unit for recognition. We propose a method for the segmentation of printed Arabic words/sub-words into characters. In the proposed method, primary and secondary strokes of the sub-words are separated and then segmentation points are identified in the primary strokes. For this, we compute the vertical projection graph for each line, which is then processed to generate a string indicating relative variations in pixels. The string is scanned further to produce characters from the sub-words. In the proposed method we use Sindhi text for segmentation into characters as its character set is the super set of Arabic. This method can be used for any other Naskh-based Arabic script such as Persian, Pashto and Urdu.

A Generalized Thinning Algorithm for Cursive and Non-Cursive Language Scripts

One of the most crucial phases in the process of text recognition is thinning of characters to a single pixel notation. The success measure of any thinning algorithm lies in its property to retain the original character shape, which are also called unit-width skeletons. No agreed universal thinning algorithm exists to produce character skeletons from different languages, which is a pre-process for all subsequent phases of character recognition such as segmentation, feature extraction, classification, etc. Written natural languages based on their intrinsic properties can be classified as cursive and non-cursive. Thinning algorithms when applied on cursive languages, poses greater complexity due to their distinct non-isolated boundaries and complex character shapes such as in Arabic, Sindhi, Urdu, etc. Such algorithms can easily be extended for parallel implementations. Selecting certain pixel arrangement grid templates over the other pixel patterns for the purpose of generating character skeletons exploits the parallel programming. The success key is in determining the right pixel arrangement grids that can reduce the cost of iterations required to evaluate each pixel for selecting for thinning or ignoring. This paper presents an improved parallel thinning algorithm, which can be easily extended for cursive or non-cursive languages alike by introducing a modified set of preservation rules via pixel arrangement grid templates, making it both robust to noise and speed. Experimental results show its success over cursive languages like Arabic, Sindhi, Urdu and non-cursive languages like English, Chinese and even numerals. Thus making it probably a universal thinning algorithm

Agent-Based User-Profiling Model for Behavior Monitoring

The growing usage of cyber resources like forums, chat groups, browsing, demands the modeling of a framework that may use an individual’s personality profile for Simulating the user’s personality in the cyberspace, Acting as a guard and guide for the respective user by determining Internet resource suitability and Monitoring & controlling the user’s social interactions with other users on the web.In this paper we exploit some notions of psychology and cognitive sciences to present a model of an Agent Framework where agents (we call “Social Agents”) monitor the activities of Internet users to build & update profiles to create socio-culture community of the similar interests in the cyberspace. Framework also guides the users what is good and what is bad for them on the Internet according to their profile.

Towards development of a trust grid to balance between organization's interests and employee's privacy

To avoid financial and other losses that occur because of insider threat an agent based profiling model was developed. When profile of the trusted user becomes mature it is analyzed and verified against organizations policy. The users are marked as suspicious if their activities are against the policies of the organizations. This paper discusses the privacy and ethical issues of the proposed model, ACENET, when it is deployed in the organization to monitor an employees activities. The paper also addresses misconception regarding security and privacy. The conventions regarding privacy policy of some standard bodies have also been referred. The tentative issues and the conflict between employer and employee that rises because of their interests have also been addressed and solution in form of Trust — Grid has been proposed. Finally, it has been concluded that in the light of provided guidelines, policy-making is the foundation to resolve all kind of probable conflicts.