Arthur J. Villasanta – Fourth Estate Contributor
Arlington, VA, United States (4E) – The private sector, which accounts for most of the world’s cyber activity, remains largely defenseless against sophisticated cyber attacks from state actors such as Russia and China. A promising solution to this massive vulnerability is called CHASE.
The U.S. Defense Advanced Research Projects Agency (DARPA) said the aim of CHASE, or the “Cyber-Hunting at Scale” program, is to develop automated tools that detect and classify novel cyberattacks; collect the right contextual data and initiate protective measures both in a business firm.
DARPA said CHASE technologies will prototype components that enable network owners to reconfigure sensors and disseminate protective measures at machine speed but under human supervision. CHASE will explore real-time investigations of potential cyber threats through “adaptive data collection.”
The threat detection algorithms developed by CHASE can be tailored to characterize and react to specific classes of threats in the context of different data types and data sources.
A key step forward in advancing CHASE was taken recently when DARPA and British multinational defense and aerospace firm, BAE Systems, began prototyping a new artificial intelligence-empowered cybersecurity technology to fight sophisticated cyberattacks engineered to bypass the best existing defenses.
CHASE counterattacks use computer automation, advanced algorithms and faster processing speed to track large volumes of data in real-time, enabling human cyber hunters to find advanced attacks otherwise hidden or buried within massive amounts of incoming data.
CHASE uses a technology called adaptive data collection to conduct real-time investigations. This tech analyzes enormous amounts of information not trackable by human defenders.
The potential of adaptive data collection is quite significant because there is often simply not enough storage and memory to monitor about 80 percent of data that goes undetected in large enterprise networks.
Experts noted cyber hunt teams are massively overburdened and can only look at a small percentage of data collected using filters. Adversaries take advantage of this. CHASE uses “adversary resistant” machine learning to defend against sophisticated cyberattacks.
The aim of machine-learning is to build automation able to organize and analyze new information by identifying patterns, placing things in context and comparing new data against very large historical databases. Emerging methods of computer automation will also be used to disseminate protective measures, said DARPA.
CHASE is now in phase one of a three-phase process that aims to bring an operational technology to the U.S. military services in about three years. For the military, CHASE aims to prototype components that enable network owners to reconfigure sensors at machine speed with appropriate levels of human supervision.
Article – All Rights Reserved.
Provided by FeedSyndicate