I am a passionate technologist with decade long experience handling IT and IT enabled Services for Government and in Corporate Sector. I built several tools in the domains of Cybersecurity and Data Science. I like to learn everyday, read everyday, grow everyday
Oct 2013 - Present, India
Mar 2023 - Present
Aug 2020 - Feb 2023
May 2015 - Jul 2018
Oct 2013 - Apr 2015
A passive OSINT tool for username recon. Tool is written in python with nil dependency of APIs of any website, whatsoever.
My Personal static blog site created using Jekyll. Retired this when I moved the contents to Hugo.
Network Intrusion Detector using Machine Learning on the KDD Cup99 dataset. Program classifies incoming connections as good or bad
This is a python implementation of the original work in the paper ‘Truth will out’, Departure-Based Process-Level Detection of Stealthy Attacks on Control Systems.
An interactive data analytics on Covid-19 Pandemic in India using GapMinder.
WExDA is a web based data exploration tool primarily useful for data preperation/ data analysis stage. This automates the EDA via web ui and is built using streamlit.
An attempt to get feet wet with Android Development. One unique feature added is the location service. Demo of the app can be found here.
The project was aimed at using various data mining techniques to analyse the partisan bias on Indian News media. Data was generated through webscrapping and insights were drawn from analytics.
Keeping in mind privacy, transparency, fairness and absolute immunity to bias and manipulation, this DApp is in Etherium blockchain using solidarity smart contracts. Demo vide can be found here
This is a python implementation of the original work in the paper Wissam Aoudi, Mikel Iturbe, and Magnus Almgren. 2018. Truth Will Out. Departure-Based Process-Level Detection of Stealthy Attacks on Control Systems. In 2018 ACM SIGSAC Conference on Computer and Communications Security (CCS ’18), October 15–19, 2018, Toronto, ON, Canada. ACM, New York, NY, USA, 15 pages. https://doi.org/10.1145/3243734.3243781
‘Curse of dimensionality’ is a well-known problem in Data Science, which often causes poor performance, inaccurate results, and, most importantly, a similarity measure break-down. The primary cause of this is because high dimensional datasets are typically sparse, and often a lower-dimensional structure or ‘Manifold’ would embed this data. So there is a non-linear relationship among the variables (or features or dimensions), which we need to learn to compute better similarity.