| Project Detail |
The basis for properly protecting data relies on being able to dynamically identify it and understanding the way it behaves,
however companies fail in achieving this today. Current solutions and technology constraints compel chief data officers
(CDO) and chief information security officers (CISO) to spend massive amount of money and resources to define and
identify sensitive data.
MinerEye has developed a proprietary technology to match data to a reference set using advanced technics applied
originally in computer vision applications and machine learning solutions, to automatically categorize, classify and track
unstructured data. This set of algorithms read the bytes of a given file and represent its content by creating a single
mathematical vector on the fly, that is constant in size and very small (few k’s) per each file.
From this point on, the system (DataTracker™) uses this vector called “signal”, that is extracted from every file it scans, for
its unsupervised clustering and further analysis tasks. This capability allows the system to process unprecedented amount of
data in a very short period (~1TB/3hrs.). The system does not dispose files from their original storage / location, opens or
changes the file but rather reads their byte stream, creates the signal on the fly and sends it out to the server. This saves
enormous network load when learning the sensitive data patterns and attributes and strengthens the non-intrusive nature of
the system. The signal can be refreshed on any scheduled basis since the data does not change in such a pace that would
affect its accuracy in the clustering process. Additionally, the scheduled scan is incremental. Powered by Interpretive AI™
Technology, MinerEye sees beyond form and file, tracking sensitive data by its essence. MinerEye does not just see
numbers, names, and file types. It sees contracts, customers’ personal data, chemical patents, most sensitive designs and
sketches, and more. |
