Focused Machine Learning for Predictive Data Loss Prevention at the Database
DB Networks patented technology is based on deep protocol analysis, asset discovery at the database discovery, and Machine Learning intelligence. As a result, you'll gain predictive visibility into a potential loss before it happens, real-time with continuous monitoring of the conversation between the database and the client with deep layer 7 protocol decode. You'll be alerted proactively, if there's an insider threat with malicious intent of data theft.

Non-intrusively discovers assets on the databases even on the non-documented databases

Pinpoints insider threats in real-time

Simplified, transparent, drop-in installation

Offers detailed insights into the interactions between applications and their connected databases

Detects policy violations in communications between the database and either the application or rogue clients

Adaptive and autonomous machine learning model construction to enable predictive capabilities before a data loss happens.

Identifies attacks intended to steal the sensitive data at the database (including Zero-Day attacks) with no signatures required



















Home / Technology
DB Networks Technology
Field Proven and Award Winning Predictive DB Data Loss Prevention Technology

While web applications can produce dynamic, and often extremely complex SQL, it turns out the applications SQL generation process can be modeled. DB Networks technology applies deep protocol analysis to all SQL statements that have been created by the applications. DB Networks then uses machine learning intelligence to construct a unique multi-dimensional behavioral model of each application. Using this unique behavioral model each SQL statement is then subjected to a thorough lexical analysis and SQL semantic analysis. Any rogue SQL statements are immediately identified and the organization's pre-defined alarm procedure is invoked.

Machine Learning Based Threat Detection

Our technology is a novel and patented approach that actually learns and models an applications unique behavior for generating its SQL statements. After a short machine-learning period, required to construct the unique behavioral model, a suite of detection algorithms evaluates each SQL statement against the application's unique behavioral model. New SQL statements, not seen during the machine learning process, go through comprehensive structural analysis. Any SQL statements not consistent with the established behavioral model are identified as likely attacks. This entire process is entirely automatic. DB Networks technology is completely plug-and-play -- requiring no blacklists, whitelists or signature files to be configured or maintain. The machine learning technique has proven to be rapid and extremely accurate at identifying insider threats and even then stealthiest of database attacks.


Technical Requirements

  • Supported databases
      Oracle server release 8i (8.1.7) or later
      Microsoft SQL Server version 7 or later
      SAP Sybase ASE version 12.5 or later
  • Network interfaces
      Two 10GigE capture port
      Four Giabit Ethernet capture ports
      One Ethernet admin port
  • DBN-6300v virtual appliance supported
    under VMware ESXi 5.1, 5.5

System Specifications

Platform
  • 2U x 19 inch rack mount form factor
  • Dual redundant power supplies -300W
Capacity
  • 2 TB of RAID10 storage for captured workloads
Connectivity
  • 480 GB High performance SSD
  • 2 TB archival storage
Security
  • Encrypted data
  • Operator authentication
  • Role based permissions to limit access to sensitive data
  • Support for encrypted database interfaces