BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Dissertation Proposal: Bishal Lakha
X-WR-TIMEZONE:Mountain Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260906T113103Z
UID:tag:localist.com\,2008:EventInstance_49330097198786
DTSTART:20250410T190000Z
DTEND:20250410T200000Z
DESCRIPTION:Dissertation Information\n\nTitle: From Detection to Explanatio
 n: Static and Temporal Graph Representation Learning Based Approach for An
 omaly Based Cyber Threats Detection\n\nProgram: Computing Ph.D. - Computer
  Science\n\nAdvisor: Dr. Edoardo Serra\n\nCommittee Members: Dr. Liljana B
 abinkostova\, Dr. Francesco Gullo\n\nAbstract\n\nOnline Intrusion Detectio
 n Systems (IDSs)—which monitor networked systems to detect ongoing cyber
 attacks through unauthorized access—are critical components of modern cy
 bersecurity infrastructure. Temporal Graph Anomaly Detection (TGAD)-based 
 IDSs have demonstrated strong potential in capturing complex and evolving 
 network behaviors. However\, current implementations often struggle with s
 calability and real-time responsiveness\, limiting their practical deploym
 ent in high-throughput environments.\n\n\nThis research aims to overcome t
 hese challenges by developing an efficient\, scalable TGAD-based IDS capab
 le of real-time anomaly detection. In addition to detecting threats as the
 y emerge\, the ability to proactively anticipate cyberattacks is essential
  for strengthening defense strategies. To this end\, this study also propo
 ses the development of a predictive framework that integrates geopolitical
  event data to forecast potential state-sponsored cyberattacks and their l
 ikely targets. These forecasts can inform and prioritize responses to dete
 cted anomalies\, enhancing situational awareness and readiness.\n\n\nFurth
 ermore\, transparency and explainability are crucial for building trust in
  automated security systems. Yet\, existing graph-based explanation method
 s often fall short in effectively interpreting detected anomalies. This di
 ssertation will therefore explore novel explanation techniques tailored sp
 ecifically to graph anomaly detection.\nTogether\, these contributions aim
  to significantly advance the scalability\, predictive capabilities\, and 
 interpretability of next-generation intrusion detection systems.
GEO:43.615223;-116.203536
LOCATION:Clearwater Building at City Center Plaza\, 368
SUMMARY:Dissertation Proposal: Bishal Lakha
URL;VALUE=URI:https://events.boisestate.edu/event/dissertation-proposal-Bis
 hal-Lakha
CATEGORIES:Lectures and Presentations
END:VEVENT
END:VCALENDAR