Internet Security

In a World where communication has become digital in all aspects, phishing emails, scams and spam messages have become very prevalent. Many phishing attempts have led to identity thefts and sensitive information (such as bank details, credit card information) being stolen and misused. While smart filters may exist in standard emails, they do not suffice to meet this challenge. We at simMachines have devised a clever algorithm that is able to find similar patterns in the emails, the addresses, the messages, header notifications etc and are able to sift and isolate these dangerous emails for the safety of a person’s credentials online.

The following demo illustrates an example of how we Display such findings in a visual manner such that a user is able to identify and classify spam emails. Please note that this demo does not demonstrate the ability of our safety algorithm, but rather shows only a segment of the full functionality, i.e. the front end interface of how such spam email IDs are clustered and displayed in an interactive manner.

Instructions:

Please visit the link mentioned at the bottom of the page to access the demo. You will be greeted to a very intricate “Pie-Chart” like diagram. This is called a Sunburst Graph. This graph intuitively classifies each “factor” used to determine if an email is a “Spam” and the individual segments and its associated side in comparison to the entire picture displays how much that factor contributes to the overall picture.

Clicking on the “Legend” tick box on the top right would display a list of all the factors, with the deeper colour indicating the factor with the most relevance. In the example below, the position of the cursor indicated how much that individual segment (and the associated factor) is associated with the entire picture (of why an email is a spam).

Clicking on each of the segment would display a new page with a bar graph that lists all the “factors” that were taken into consideration when identifying an email as a “Spam”. This visualization is part of our “Justification” rather than just providing a prediction by saying whether an email is spam or not. We are able to provide specific reasons why an email containing these factors is identified to be a spam. Moreover, the order in which the bars are arranged indicates how much each factor is important for this specific decision.