BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Chicago BEGIN:DAYLIGHT DTSTART:20230312T030000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:CDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20231105T010000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20230508T223743Z UID:8C66DC3C-E7A8-4AEF-B94D-19845CCCFD9F DTSTART;TZID=America/Chicago:20230505T133000 DTEND;TZID=America/Chicago:20230505T150000 DESCRIPTION:Speaker - Dr. Vijay Mishra\, Army Research Labs\n\nComplex and dynamic environments in many engineering applications require intelligent and autonomous agents that cognitively sense the environment\, acquire the relevant information\, and then use it to adapt in real-time for improved performance. In this context\, inverse cognition --- wherein a 'defender' agent learns the information about itself sensed by a cognitive 'attacker ' agent --- has recently gathered significant research interest. The probl em is motivated by the need to design counter-autonomous adversarial syste ms. A suitable example is a military surveillance application\, where a ta rget aircraft is tracked by a hostile but cognitive radar\, which is equip ped with a Bayesian tracker. It is then instructive for the target to beco me inversely cognitive and predict the actions of the radar and guard agai nst them. This is precisely the objective of inverse Bayesian filtering\, wherein given noisy observations\, a posterior distribution of the underly ing state is obtained. In particular\, we consider this problem in a non-l inear setting and develop a family of inverse stochastic filters to addres s inverse cognition. We begin with the inverse extended Kalman filter (I-E KF) and derive its theoretical stability guarantees using both bounded non linearity and unknown matrix approaches. We then generalize these formulat ions and results to the case of higher-order\, Gaussian-sum\, and dithered I-EKFs. We then obtain a more robust approach to nonlinearities in the fo rm of an inverse unscented Kalman filter (I-UKF) and extend it to inverse cubature/quadrature Kalman filters (I-CKF/I-UKF). For both I-EKF and I-UKF \, we also consider the scenario when the radar's filter is unknown to the target. This work has strong connections with general approximate Bayesia n inference approaches in machine learning. The UKF\, QKF\, and CKF are a special case of assumed density filters (ADF) or online Bayesian learning\ , which sequentially approximates the posterior distribution of the underl ying state. We close this talk by discussing the recent advances in meta-c ognitive radar.\n\nSpeaker(s): Vijay Mishra\, \n\nRoom: Room 430\, Bldg: S AN PEDRO 1 BUILDING\, 4thFloor\, 506 Dolorosa St\, San Antonio\, Texas\, U nited States\, 78204 LOCATION:Room: Room 430\, Bldg: SAN PEDRO 1 BUILDING\, 4thFloor\, 506 Dolor osa St\, San Antonio\, Texas\, United States\, 78204 ORGANIZER:garrett.hall@my.utsa.edu SEQUENCE:6 SUMMARY:IEEE AESS - DL - Inverse Cognition and Counter-Adversarial Learning in Radar URL;VALUE=URI:https://events.vtools.ieee.org/m/348346 X-ALT-DESC:Description: <br /><p>Speaker - Dr. Vijay Mishra\, Army Research Labs</p>\n<p>Complex and dynamic environments in many engineering applica tions require intelligent and autonomous agents that cognitively sense the environment\, acquire the relevant information\, and then use it to adapt in real-time for improved performance. In this context\, inverse cognitio n --- wherein a 'defender' agent learns the information about itself sense d by a cognitive 'attacker' agent &nbsp\;--- has recently gathered signifi cant research interest. The problem is motivated by the need to design cou nter-autonomous adversarial systems. A suitable example is a military surv eillance application\, where a target aircraft is tracked by a hostile but cognitive radar\, which is equipped with a Bayesian tracker. It is then i nstructive for the target to become inversely cognitive and predict the ac tions of the radar and guard against them. This is precisely the objective of inverse Bayesian filtering\, wherein given noisy observations\, a post erior distribution of the underlying state is obtained. In particular\, we consider this problem in a non-linear setting and develop a family of inv erse stochastic filters to address inverse cognition. We begin with the in verse extended Kalman filter (I-EKF) and derive its theoretical stability guarantees using both bounded nonlinearity and unknown matrix approaches. We then generalize these formulations and results to the case of higher-or der\, Gaussian-sum\, and dithered I-EKFs. We then obtain a more robust app roach to nonlinearities in the form of an inverse unscented Kalman filter (I-UKF) and extend it to inverse cubature/quadrature Kalman filters (I-CKF /I-UKF). For both I-EKF and I-UKF\, we also consider the scenario when the radar's filter is unknown to the target. This work has strong connections with general approximate Bayesian inference approaches in machine learnin g. The UKF\, QKF\, and CKF are a special case of assumed density filters ( ADF) or online Bayesian learning\, which sequentially approximates the pos terior distribution of the underlying state. We close this talk by discuss ing&nbsp\;the recent advances in meta-cognitive radar.</p> END:VEVENT END:VCALENDAR