December 15th, 2015

CYR3CON's Machine Learning Platform Predicted Exploits Later Used by State-Sponsored Hackers

TEMPE, Ariz., Oct. 21, 2020 /PRNewswire-PRWeb/ -- CYR3CON®, which created and sells a machine learning solution for predicting the actions of hackers, announced today it had successfully predicted vulnerabilities used by Chinese state-sponsored hackers. The vulnerabilities used by the Chinese hackers were described in an Oct. 20th advisory issued by the National Security Agency (NSA).

Prior to the NSA advisory, the CYR3CON machine learning platform had collected and analyzed intelligence relevant to all 25 software vulnerabilities. These vulnerabilities were described by NSA advisory as "known to be recently leveraged, or scanned-for, by Chinese state-sponsored cyber actors to enable successful hacking operations against a multitude of victim networks." 24 of the 25 vulnerabilities were predicted as being at least 3 times as likely to be used by hackers than average; with 21 of the vulnerabilities reaching the maximum score by CYR3CON's machine learning scoring system known as CyRating®.

"This is a great example of how machine learning can impact cybersecurity," stated Paulo Shakarian, CEO and co-founder of CYR3CON. "We are very proud to say that CYR3CON customers were well aware of the risks posed by these vulnerabilities months ahead of the NSA advisory. CYR3CON's warnings about these vulnerabilities were provided with a very low false positive rate."

The NSA advisory revealed that hackers will often leverage vulnerabilities deemed as "medium" severity. Over 98% of vulnerabilities are ranked as "medium" or higher according to the National Institute of Standards. About 20% of the vulnerabilities described in the advisory fall in this category. "Medium" vulnerabilities often are overlooked by security teams. An additional 16% of the vulnerabilities in the advisory were from years prior to 2019 – another source of flaws often unpatched by defenders. All of the medium and older vulnerabilities were predicted in advance of the advisory by CYR3CON's platform.

The NSA acknowledged the shortcomings of existing methods of prioritization. In a statement issued in their press release, NSA Cybersecurity Director Anne Neuberger remarked that "it can be hard to prioritize patching and mitigation efforts."

"The use of machine learning – combined with intelligence – is the best way to scale prediction and get ahead of the hackers," Shakarian stated. "The NSA advisory shows very clearly that existing methods fall short in their ability to advise companies on what is most important to protect because those methods do not consider the adversary."

CYR3CON's machine learning technology was originally developed under IARPA funding (a US government activity) and has undergone extensive peer-review. Recently, the firm has raised venture capital to continue its growth trajectory. The solution is offered as a SaaS-based offering and the company also engages clients with a "Predictive Threat Assessment" that can be automatically performed with the platform. The Predictive Threat Assessment allows security professionals to pick-out vulnerabilities that may be used in future attacks – such as the ones described in the NSA's advisory.


CYR3CON provides the only machine learning threat intelligence platform that predicts and prioritizes the latest cyber threats, enabling CISO's to better understand the threat landscape, gain knowledge about malicious hacker behavior, and identify emerging attacks against enterprises. CYR3CON's underlying algorithms are also the only offering validated through years of academic research, peer reviewed publication, and government backed grants. For more information, please visit



Data & News supplied by
Stock quotes supplied by Barchart
Quotes delayed at least 20 minutes.
By accessing this page, you agree to the following
Privacy Policy and Terms and Conditions.