A method, system and computer-usable medium for adaptively assessing risk associated with an endpoint, comprising: determining a risk level corresponding to an entity associated with an endpoint; selecting a frequency and a duration of an endpoint monitoring interval; collecting user behavior to collect user behavior associated with the entity for the duration of the endpoint monitoring interval via the endpoint; processing the user behavior to generate a current risk score for the entity; comparing the current risk score of the user to historical risk scores to determine whether a risk score of a user has changed; and changing the risk score of the user to the current risk score when the risk score of the user has changed.
Gracefully Handling Endpoint Feedback When Starting To Monitor
A method, system and computer-usable medium for adaptively assessing risk associated with an endpoint, comprising: determining a risk level corresponding to an entity associated with an endpoint; selecting a frequency and a duration of an endpoint monitoring interval; collecting user behavior to collect user behavior associated with the entity for the duration of the endpoint monitoring interval via the endpoint; processing the user behavior to generate a current risk score for the entity; comparing the current risk score of the user to historical risk scores to determine whether a risk score of a user has changed; and changing the risk score of the user to the current risk score when the risk score of the user has changed.
A method, system and computer-usable medium for generating session-based security information. Generating the session-based security information includes the steps of monitoring user behavior between an enactor and an entity; detecting user behavior data associated with the user behavior; generating a session using the user behavior data, the session relating to an entity discrete interaction of the enactor; and, associating the session and the session-based security information with the user profile.
A method, system and computer-usable medium for adaptively remediating multivariate risk, comprising: detecting a violation of a multivariate security policy, the multivariate security policy comprising a plurality of variables; identifying a variable from the plurality of variables associated with a cause of the violation; associating an entity with the variable associated with the cause of the violation; and, adaptively remediating a risk associated with the entity.
- Austin TX, US Richard A. Ford - Austin TX, US Ann Irvine - Baltimore MD, US Kristin Machacek Leary - Austin TX, US
International Classification:
H04L 29/06 G06Q 10/06
Abstract:
A method, system, and computer-usable medium for protecting against contagion-based risk events are disclosed for monitoring behavior of users to construct a contagion network relationship map of connection and influence relationships between different users and then analyzing a received stream of events from the users to identify a critical event performed by a first user having a first risk score so that one or more propagated risk scores can be generated from the first risk score for at least a first connected user based on connection and influence relationships between the first user and the first connected user that are extracted from the contagion network relationship so that an adaptive response may be automatically generated to protect and control against actions by at least the first connected user based on the one or more propagated risk scores.
Identifying Security Risks Using Distributions Of Characteristic Features Extracted From A Plurality Of Events
- Austin TX, US Christopher Poirel - Baltimore MD, US Ann Irvine - Baltimore MD, US
International Classification:
H04L 29/06 G06F 17/30
Abstract:
A method, system and computer-usable medium for constructing a distribution of interrelated event features. The constructing a distribution of interrelated event features includes receiving a stream of events, the stream of events comprising a plurality of events; extracting features from the plurality of events; constructing a distribution of the features from the plurality of events; and, analyzing the distribution of the features from the plurality of events.
Identifying Security Risks Using Distributions Of Characteristic Features Extracted From A Plurality Of Events
- Austin TX, US Christopher Poirel - Baltimore MD, US Ann Irvine - Baltimore MD, US
International Classification:
H04L 29/06 G06F 16/28
Abstract:
A method, system and computer-usable medium are disclosed for identifying security risks to a computer system based on a distribution of categorical features of events. Certain embodiments are directed to a computer-implemented method comprising: receiving a stream of events, the stream of events including a plurality of events; extracting a categorical feature from the plurality of events, where the categorical feature includes a set of categorical feature members, where the set of categorical feature members are generated on the fly from string values included in the extracted categorical feature; constructing a distribution for the categorical feature based on categorical feature members extracted from the plurality of events; and, analyzing the distribution of the categorical feature to identify one or more security risk factors.
Gracefully Handling Endpoint Feedback When Starting To Monitor
A method, system and computer-usable medium for adaptively assessing risk associated with an endpoint, comprising: determining a risk level corresponding to an entity associated with an endpoint; selecting a frequency and a duration of an endpoint monitoring interval; collecting user behavior to collect user behavior associated with the entity for the duration of the endpoint monitoring interval via the endpoint; processing the user behavior to generate a current risk score for the entity; comparing the current risk score of the user to historical risk scores to determine whether a risk score of a user has changed; and changing the risk score of the user to the current risk score when the risk score of the user has changed.
Arceo.ai
Head of Data Science
Forcepoint Jan 2018 - Jul 2018
Chief Data Scientist, User and Data Security
Forcepoint Aug 2017 - Jan 2018
Principal Data Scientist
Redowl Analytics Aug 2015 - Aug 2017
Principal Data Scientist at Redowl Analytics
Redowl Analytics Jul 2014 - Aug 2015
Senior Data Scientist
Education:
The Johns Hopkins University 2008 - 2014
Doctorates, Doctor of Philosophy, Computer Science, Philosophy
University of North Carolina at Chapel Hill 2006 - 2008
Master of Science, Masters, Information Science
Dartmouth College 2002 - 2006
Bachelors, Mathematics, Social Sciences, Social Science
Parry Mccluer High School 2002