Patents by Inventor Erik M. Ferragut
Erik M. Ferragut has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10929529Abstract: A cyber-security threat detection system and method stores physical data measurements from a cyber-physical system and extracts synchronized measurement vectors synchronized to one or more timing pulses. The system and method synthesize data integrity attacks in response to the physical data measurements and applies alternating parameterized linear and non-linear operations in response to the synthesized data integrity attacks. The synthesis renders optimized model parameters used to detect multiple cyber-attacks.Type: GrantFiled: January 28, 2020Date of Patent: February 23, 2021Assignee: UT-BATTELLE, LLCInventors: Erik M. Ferragut, Jason A. Laska
-
Publication number: 20200226251Abstract: A cyber-security threat detection system and method stores physical data measurements from a cyber-physical system and extracts synchronized measurement vectors synchronized to one or more timing pulses. The system and method synthesize data integrity attacks in response to the physical data measurements and applies alternating parametrized linear and non-linear operations in response to the synthesized data integrity attacks. The synthesis renders optimized model parameters used to detect multiple cyber-attacks.Type: ApplicationFiled: January 28, 2020Publication date: July 16, 2020Inventors: Erik M. Ferragut, Jason A. Laska
-
Patent number: 10572659Abstract: A cyber-security threat detection system and method stores physical data measurements from a cyber-physical system and extracts synchronized measurement vectors synchronized to one or more timing pulses. The system and method synthesizes data integrity attacks in response to the physical data measurements and applies alternating parametrized linear and non-linear operations in response to the synthesized data integrity attacks. The synthesis renders optimized model parameters used to detect multiple cyber-attacks.Type: GrantFiled: September 19, 2017Date of Patent: February 25, 2020Assignee: UT-Battelle, LLCInventors: Erik M. Ferragut, Jason A. Laska
-
Publication number: 20180082058Abstract: A cyber-security threat detection system and method stores physical data measurements from a cyber-physical system and extracts synchronized measurement vectors synchronized to one or more timing pulses. The system and method synthesizes data integrity attacks in response to the physical data measurements and applies alternating parametrized linear and non-linear operations in response to the synthesized data integrity attacks. The synthesis renders optimized model parameters used to detect multiple cyber-attacks.Type: ApplicationFiled: September 19, 2017Publication date: March 22, 2018Inventors: Erik M. Ferragut, Jason A. Laska
-
Patent number: 9361463Abstract: A system is described for receiving a stream of events and scoring the events based on anomalousness and maliciousness (or other classification). The system can include a plurality of anomaly detectors that together implement an algorithm to identify low-probability events and detect atypical traffic patterns. The anomaly detector provides for comparability of disparate sources of data (e.g., network flow data and firewall logs.) Additionally, the anomaly detector allows for regulatability, meaning that the algorithm can be user configurable to adjust a number of false alerts. The anomaly detector can be used for a variety of probability density functions, including normal Gaussian distributions, irregular distributions, as well as functions associated with continuous or discrete variables.Type: GrantFiled: December 11, 2013Date of Patent: June 7, 2016Assignee: UT-Batelle, LLCInventors: Erik M. Ferragut, Jason A. Laska, Robert A. Bridges
-
Patent number: 9319421Abstract: A system is described for receiving a stream of events and scoring the events based on anomalousness and maliciousness (or other classification). The events can be displayed to a user in user-defined groupings in an animated fashion. The system can include a plurality of anomaly detectors that together implement an algorithm to identify low probability events and detect atypical traffic patterns. The atypical traffic patterns can then be classified as being of interest or not. In one particular example, in a network environment, the classification can be whether the network traffic is malicious or not.Type: GrantFiled: October 14, 2013Date of Patent: April 19, 2016Assignee: UT-Battelle, LLCInventors: Erik M. Ferragut, John R. Goodall, Michael D. Iannacone, Jason A. Laska, Lane T. Harrison
-
Publication number: 20150161394Abstract: A system is described for receiving a stream of events and scoring the events based on anomalousness and maliciousness (or other classification). The system can include a plurality of anomaly detectors that together implement an algorithm to identify low-probability events and detect atypical traffic patterns. The anomaly detector provides for comparability of disparate sources of data (e.g., network flow data and firewall logs.) Additionally, the anomaly detector allows for regulatability, meaning that the algorithm can be user configurable to adjust a number of false alerts. The anomaly detector can be used for a variety of probability density functions, including normal Gaussian distributions, irregular distributions, as well as functions associated with continuous or discrete variables.Type: ApplicationFiled: December 11, 2013Publication date: June 11, 2015Applicant: UT-Battelle, LLCInventors: Erik M. Ferragut, Jason A. Laska, Robert A. Bridges
-
Publication number: 20150106927Abstract: A system is described for receiving a stream of events and scoring the events based on anomalousness and maliciousness (or other classification). The events can be displayed to a user in user-defined groupings in an animated fashion. The system can include a plurality of anomaly detectors that together implement an algorithm to identify low probability events and detect atypical traffic patterns. The atypical traffic patterns can then be classified as being of interest or not. In one particular example, in a network environment, the classification can be whether the network traffic is malicious or not.Type: ApplicationFiled: October 14, 2013Publication date: April 16, 2015Applicant: UT-Battelle, LLCInventors: Erik M. Ferragut, John R. Goodall, Michael D. Iannacone, Jason A. Laska, Lane T. Harrison
-
Patent number: 8762188Abstract: A system evaluates reliability, performance and/or safety by automatically assessing the targeted system's requirements. A cost metric quantifies the impact of failures as a function of failure cost per unit of time. The metrics or measurements may render real-time (or near real-time) outcomes by initiating active response against one or more high ranked threats. The system may support or may be executed in many domains including physical domains, cyber security domains, cyber-physical domains, infrastructure domains, etc. or any other domains that are subject to a threat or a loss.Type: GrantFiled: April 10, 2012Date of Patent: June 24, 2014Assignee: UT-Battelle, LLCInventors: Robert K. Abercrombie, Frederick T. Sheldon, Erik M. Ferragut
-
Publication number: 20120232679Abstract: A system evaluates reliability, performance and/or safety by automatically assessing the targeted system's requirements. A cost metric quantifies the impact of failures as a function of failure cost per unit of time. The metrics or measurements may render real-time (or near real-time) outcomes by initiating active response against one or more high ranked threats. The system may support or may be executed in many domains including physical domains, cyber security domains, cyber-physical domains, infrastructure domains, etc. or any other domains that are subject to a threat or a loss.Type: ApplicationFiled: April 10, 2012Publication date: September 13, 2012Inventors: Robert K. Abercrombie, Frederick Sheldon, Erik M. Ferragut