BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://github.com/derhansen/sf_event_mgt
METHOD:PUBLISH
BEGIN:VEVENT
UID:4987-3849@fg-netsec.gi.de
CLASS: PUBLIC
SUMMARY:NetSec Lecture Series: DEEPCASE: Semi-Supervised Contextual Analysi
 s of Security Events
DESCRIPTION:Die Fachgruppe Sicherheit in Mobil- und Festnetzen veranstaltet
  in diesem Sommersemester die virtuelle NetSec Lecture Series. Die dritte V
 eranstaltung findet am 15. Juni 2022 von 17:00 - 18:30 Uhr statt. Die Zoom-
 Einwahldaten für die Veranstaltung sind: https://tu-berlin.zoom.us/j/632235
 49564?pwd=SUdRSjcvVzJJeVhielM0UE5pNGhlQT09.  Save-the-date: NetSec Lecture 
 Series\n\n 	15. Juni 2022: Prof. Dr. Andreas Peter, Universität Oldenburg 	
 DEEPCASE: Semi-Supervised Contextual Analysis of Security Events \n\n\n\nAm
  15. Juni 2022 findet der dritte Vortrag der NetSec Lecture Series statt. P
 rof. Dr. Andreas Peter von der Universität Oldenburg wird über die Analyse 
 von IT-Sicherheitsereignissen sprechen.\n\nDEEPCASE: Semi-Supervised Contex
 tual Analysis of Security Events\n\nAbstract: Security monitoring systems d
 etect potentially malicious activities in IT infrastructures, by either loo
 king for known signatures or for anomalous behavior. Security operators inv
 estigate associated security events to determine whether they pose a threat
  to their organization. In many cases, a single event may be insufficient t
 o determine whether certain activity is indeed malicious. Therefore, a secu
 rity operator frequently needs to correlate multiple events to identify if 
 they pose a real threat. Unfortunately, the vast number of events that need
  to be correlated often overload security operators, forcing them to ignore
  some events and, thereby, potentially miss attacks.\n\nIn this presentatio
 n, we will talk about how to automatically correlate security events and, t
 hus, automate parts of the security operator's workload. Concretely, we wil
 l look at the design and evaluation of DeepCASE, a system that leverages th
 e context around events to determine which events require further inspectio
 n. This approach reduces the number of events that need to be inspected. In
  addition, the context provides valuable insights into why certain events a
 re classified as malicious. We show that DeepCASE automatically filters 86.
 72% of the events and reduces the manual workload of security operators by 
 90.53%, while underestimating the risk of potential threats in less than 0.
 001% of cases.\n\nCV: Andreas Peter is a professor in computer science at t
 he Carl von Ossietzky University of Oldenburg in Germany, where he leads th
 e research group on Safety-Security-Interaction. He is also a visiting prof
 essor in IT-security at the University of Twente in the Netherlands. His cu
 rrent research interests include both fundamental and applied security and 
 privacy aspects in IT systems, particularly in the context of safety-critic
 al systems and the Internet of Things.\n\nProf. Peter studied mathematics a
 t the Universities of Oldenburg and Cambridge (England) and received his do
 ctorate in computer science from the Technical University of Darmstadt in 2
 013. He then worked at the University of Twente, initially as a research as
 sistant, then from 2014 to 2018 as assistant professor and later as profess
 or in IT-security at the computer science department. In 2022, he took on t
 he professorship in Oldenburg. Prof. Peter is an editorial board member of 
 the EURASIP Journal on Information Security and regularly serves on the pro
 gram committees of several workshops and conferences devoted to security an
 d privacy.\n\n\n\nVergangene Veranstaltungen der NetSec Lecture Series:\n\n
  	21. April 2022: Dr. Robin Sommer (ICSI/Corelight) 	Transition To Practice
 , They Say: 	How Two Decades of Security Research Ultimately Spawned a Sili
 con Valley Startup 	19. Mai 2022: Jens Hiller (RWTH Aachen) 	Tracking the d
 eployment of TLS 1.3 on the Web: A story of experimentation and centralizat
 ion 
LOCATION:Online
DTSTAMP:20220713T093913Z
DTSTART:20220615T150000Z
DTEND:20220615T163000Z
END:VEVENT
END:VCALENDAR