BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Drupal iCal API//EN X-WR-CALNAME:Events items teaser X-WR-TIMEZONE:America/Toronto BEGIN:VTIMEZONE TZID:America/Toronto X-LIC-LOCATION:America/Toronto BEGIN:DAYLIGHT TZNAME:EDT TZOFFSETFROM:-0500 TZOFFSETTO:-0400 DTSTART:20230312T070000 END:DAYLIGHT BEGIN:STANDARD TZNAME:EST TZOFFSETFROM:-0400 TZOFFSETTO:-0500 DTSTART:20221106T060000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT UID:6830bd4bbfa91 DTSTART;TZID=America/Toronto:20230606T130000 SEQUENCE:0 TRANSP:TRANSPARENT DTEND;TZID=America/Toronto:20230606T140000 URL:/computer-science/events/phd-seminar-machine-learni ng-exploring-the-limits-of-model-targeted-indiscriminate-data-poisoning-at tacks SUMMARY:PhD Seminar • Machine Learning • Exploring the Limits of\nModel -Targeted Indiscriminate Data Poisoning Attacks CLASS:PUBLIC DESCRIPTION:Summary \n\nPLEASE NOTE: THIS PHD SEMINAR WILL TAKE PLACE IN DC 1304 AND\nVIRTUALLY.\n\nYIWEI LU\, PHD CANDIDATE\n_David R. Cheriton Scho ol of Computer Science_\n\nSUPERVISOR: Professor Yaoliang Yu\n\nIndiscrimi nate data poisoning attacks aim to decrease a model’s test\naccuracy by injecting a small amount of corrupted training data.\nDespite significant interest\, existing attacks remain relatively\nineffective against modern machine learning (ML) architectures.\n DTSTAMP:20250523T182411Z END:VEVENT END:VCALENDAR