THE PURPOSE OF THIS AGREEMENT IS TO FUND RESEARCH SUPPORTING THE DEFENSE ADVANCED RESEARCH PROJECTS AGENCY DARPA GUARANTEEING AI ROBUSTNESS AGAINST DECEPTION GARD PROGRAM. THIS EFFORT SHALL BE CARRIED OUT GENERALLY AS SET FORTH IN EXHIBIT B, RESEARCH DESCRIPTION DOCUMENT, DATED DECEMBER 18, 2019, AND IN THE RECIPIENT PROPOSAL TITLED, LR2 LEARNING ROBUST REPRESENTATIONS, SUBMITTED ON APRIL 11, 2019, COPIES OF WHICH ARE IN THE POSSESSION OF BOTH PARTIES. THE TERM OF THE BASE PERIOD FOR THIS AGREEMENT COMMENCES ON THE EFFECTIVE DATE OF THE AWARD AND CONTINUES FOR TWELVE 12 MONTHS AFTER AWARD.