PatternEx™, the pioneer in Artificial Intelligence for information security, today launched the company and its PatternEx Threat Prediction Platform that creates "virtual security analysts" that mimic the intuition of human security analysts in real time and at scale. Based on real world datasets, the PatternEx Threat Prediction Platform detects ten times more threats with five times fewer false positives compared with approaches based on Machine Learning-Anomaly Detection technology.
The PatternEx solution introduces a new technology called "Active Contextual Modeling™" or ACM, that synthesizes analyst intuition into predictive models. These models, when deployed across global customers, can learn from each other and achieve a network effect in detecting attack patterns.
"The most frustrating thing in InfoSec is that the data to detect malicious behavior often already exists in enterprise infrastructures today," notes Uday Veeramachaneni, PatternEx CEO and co-founder. "The human analysts can detect it, but analysts are difficult to hire and are not scalable. The only way to get real time detection is to be able to mimic those analysts using artificial intelligence based on ACM technology."
The ACM technology transforms raw data into behaviors, and synthesizes analyst intuition into predictive models; the Platform then leverages these models to make real time predictions about specific threat vectors. The more attacks the system predicts, the more feedback it receives from the analysts, which in turn improves the accuracy of future predictions.
"Machine learning models are good at establishing baselines and detecting anomalies to those baselines, but they are not capable of knowing if those anomalies represent good or bad behavior unless humans tell them so," comments Avivah Litan, Gartner VP Distinguished Analyst in her report on user and entity behavior analytics published last September.*
As the platform learns a predictive model from one customer environment, this knowledge can be transferred between enterprises to detect threats globally and converge on new attacks at faster speeds for all customers, commonly known as a network effect.
"Artificial Intelligence holds great promise for InfoSec," says Tim Mather, Chief Information Security Officer for Cadence Design Systems. "In addition to being able to detect threats without relying on rules, AI could enable a network effect whereby an attack pattern detected at one organization can be transferred to another organization in the network. At Cadence, we are piloting the PatternEx Threat Prediction Platform for Data Exfiltration and early results are encouraging."
The PatternEx solution includes a number of novel components combined into a single platform:
- a big data platform designed for large data volumes and real time response
- an ensemble of algorithms designed to detect rare behaviors with the goal of identifying new attacks
- a mechanism to obtain feedback from security analysts and continuously update models with the provided feedback.
- an active learning feedback loop that continuously improves detection rates over time
- a repository of threat intelligence that can be shared among enterprises
Ultimately, PatternEx customers gain more visibility, detection, control of malicious behavior for both fraud and breach, without the confusing noise of false positives and the increased security staff they demand. In addition, the PatternEx Threat Prediction Platform is easy to integrate and deploy into existing security architectures.
The Threat Prediction Platform is available as software on premise, in the cloud, or in a private cloud. The Platform is the result of two years of development by a team of AI, security, and distributed systems experts.
*Gartner, Market Guide for User and Entity Behavior Analytics, Avivah Litan, 22 September 2015