BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260125T072715Z UID:92153FE8-383F-40FF-977E-3D78A2D1CB51 DTSTART;TZID=America/Los_Angeles:20260116T130000 DTEND;TZID=America/Los_Angeles:20260116T143000 DESCRIPTION:As cyber-attacks grow increasingly sophisticated and large-scal e\, they present escalating challenges to the security of modern networked systems. This presentation reviews recent advances in cyber-attack detect ion through machine learning and deep learning\, examining their capabilit ies as well as their current limitations. I will share my recent research on integrating forecasting\, anomaly detection\, explainable AI\, and larg e language models (LLMs) to develop intelligent and autonomous mitigation frameworks. The talk will conclude by outlining future directions for next -generation cyber defense\, with a focus on explainability\, privacy-prese rving techniques\, and adaptive response mechanisms.\n\nSpeaker(s): Sajal Saha\, \n\nRoom: 4520\, Bldg: Building 10\, 3333 University Way\, Prince G eorge\, British Columbia\, Canada\, V2N 4Z9 LOCATION:Room: 4520\, Bldg: Building 10\, 3333 University Way\, Prince Geor ge\, British Columbia\, Canada\, V2N 4Z9 ORGANIZER:Fan.Jiang@unbc.ca SEQUENCE:21 SUMMARY:Advancing Cyber Defense Systems through Machine Learning\, Deep Lea rning\, and Large Language Models URL;VALUE=URI:https://events.vtools.ieee.org/m/532614 X-ALT-DESC:Description: <br /><p>As cyber-attacks grow increasingly sophist icated and large-scale\, they present escalating challenges to the securit y of modern networked systems. This presentation reviews recent advances i n cyber-attack detection through machine learning and deep learning\, exam ining their capabilities as well as their current limitations. I will shar e my recent research on integrating forecasting\, anomaly detection\, expl ainable AI\, and large language models (LLMs) to develop intelligent and a utonomous mitigation frameworks. The talk will conclude by outlining futur e directions for next-generation cyber defense\, with a focus on explainab ility\, privacy-preserving techniques\, and adaptive response mechanisms.< /p> END:VEVENT END:VCALENDAR