Show simple item record

dc.contributor.authorFansler, Aaron A.D.
dc.dateJuly 20, 2018
dc.date.accessioned2018-09-07T19:58:03Z
dc.date.available2018-09-07T19:58:03Z
dc.date.issued2018-07-20
dc.identifier.urihttps://hdl.handle.net/10945/59919
dc.descriptionNPS Defense Energy Seminaren_US
dc.description.abstractMr. Fansler presentation will discuss the use of machine learning in cyber security. Some significant steps have been made in the I.T. world but not in the O.T. world. The only advances come from the attacker’s side where they are now getting smarter and faster. Their success is accomplished by implementing machine learning algorithms. Machine learning is a branch of computer science aimed at enabling computers to learn new behaviors based on empirical data. The goal is to design algorithms that allow a computer to display behavior learned from past experience, rather than human interaction. Machine learning is a rapidly developing field at the intersection of statistics, computer science, and applied mathematics, and it is having transformative impact across the engineering and natural sciences. In the past, Machine Learning has not had as much success in cyber security as in other fields. Many early attempts struggled with problems such as generating too many false positives, which resulted in mixed attitudes towards it. Some have argued that that while machine learning is very good at finding similarities, it is less successful at finding anomalies and therefore not suited to Cyber Security. On the other side, cybersecurity is “basically broken” and machine learning is one of the few ‘beacons of hope.’ Mr. Fansler will present his opinion of the latter. Machine learning will enable 24/7/365 monitoring of larger data loads. It will still require human interaction and intervention. Machine learning will require tuning and lots of learning in order to accurately filter real attacks from what appear suspicious but are actually benign activity. It will complement traditional defenses to create a more multi-layered defense. It is inevitable that this is where the future of cyber security is. Ampex’s objective is to design, develop, and demonstrate the use of distributed machine learning techniques in a mesh network to optimize sharing of Graphics Processing Units (GPUs) across platforms which will will provide a cyber-capability created specifically for control systems in the form of a high speed, high capacity, rugged computer devices, which, can detect, define, analyze, and mitigate cyber threats and vulnerabilities.en_US
dc.format.extentDuration: 1:11:17 Filesize 598.2 MBen_US
dc.language.isoen_US
dc.publisherNaval Postgraduate School, Monterey, Californiaen_US
dc.rightsThis publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.en_US
dc.titleNon-Traditional Attack Surfaces to CIP and IIOT Networks [video]en_US
dc.typeVideoen_US
dc.contributor.corporateNaval Postgraduate School (U.S.)


Files in this item

Icon
Thumbnail

This item appears in the following Collection(s)

Show simple item record