BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241014T032401Z
UID:51FB3CB9-AA63-4050-8841-271A3BBD5B44
DTSTART;TZID=America/New_York:20241010T230000
DTEND;TZID=America/New_York:20241011T000000
DESCRIPTION:Talk abstract: Cellular network security is more critical than 
 ever\, given the increased complexity of these networks and the numbers of
  applications that depend on them\, including telehealth\, remote educatio
 n\, ubiquitous robotics and autonomous vehicles\, smart cities\, and Indus
 try 4.0. In order to devise more effective defenses\, a recent trend is to
  leverage machine learning (ML) techniques\, which have become applicable 
 because of today advanced capabilities for collecting data as well high-pe
 rformance computing systems for training of ML models. Recent large langua
 ge models (LLMs) are also opening new interesting directions for security 
 applications. In this talk\, I will first present a comprehensive threat a
 nalysis in the context of 5G cellular networks to give a concrete example 
 of the magnitude of the problem of cellular network security. Then\, I wil
 l present two specific applications of ML techniques for the security of c
 ellular networks. The first application focuses on the use of natural lang
 uage processing techniques to the problem of detecting inconsistencies in 
 the "natural language specifications" of cellular network protocols. The s
 econd application addresses the design of an anomaly detection system able
  to detect the presence of malicious base stations and determine the type 
 of attack. Then I'll conclude with a discussion on research directions.\n\
 nSpeaker(s): Elisa Bertino\, \n\nRoom: Room 316 (3rd floor theatre space)\
 , Bldg: Information Science Building\, 135 N Bellefield Ave\, Pittsburgh\,
  Pennsylvania\, United States\, 15260
LOCATION:Room: Room 316 (3rd floor theatre space)\, Bldg: Information Scien
 ce Building\, 135 N Bellefield Ave\, Pittsburgh\, Pennsylvania\, United St
 ates\, 15260
ORGANIZER:bpalan@pitt.edu
SEQUENCE:11
SUMMARY:Applying Machine Learning to Securing Cellular Networks
URL;VALUE=URI:https://events.vtools.ieee.org/m/436148
X-ALT-DESC:Description: <br /><p class="MsoNormal" style="text-align: justi
 fy\;"><strong><span style="font-size: 13.0pt\; font-family: 'Times'\,serif
 \; mso-fareast-font-family: 'Times New Roman'\; mso-bidi-font-family: Cali
 bri\; color: black\;">Talk&nbsp\;abstract</span></strong><span style="font
 -size: 13.0pt\; font-family: 'Times'\,serif\; mso-fareast-font-family: 'Ti
 mes New Roman'\; mso-bidi-font-family: Calibri\; color: black\;">: Cellula
 r network security is more critical than ever\, given the increased comple
 xity of these networks and the numbers of applications that depend on them
 \, including telehealth\, remote education\, ubiquitous robotics and auton
 omous vehicles\, smart cities\, and Industry 4.0. In order to devise more 
 effective defenses\, a recent trend is to leverage machine learning (ML) t
 echniques\, which have become applicable because of today advanced capabil
 ities for collecting data as well high-performance computing systems for t
 raining of ML models. Recent large language models (LLMs) are also opening
  new interesting directions for security applications.&nbsp\; In this&nbsp
 \;talk\, I will first present a comprehensive threat analysis in the conte
 xt of 5G cellular networks to give a concrete example of the magnitude of 
 the problem of cellular network security. Then\, I will present two specif
 ic applications of ML techniques for the security of cellular networks. Th
 e first application focuses on the use of natural language processing tech
 niques to the problem of detecting inconsistencies in the "natural languag
 e specifications" of cellular network protocols. The second application ad
 dresses the design of an anomaly detection system able to detect the prese
 nce of malicious base stations and determine the type of attack. Then I'll
  conclude with a discussion on research directions.</span></p>
END:VEVENT
END:VCALENDAR