BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME:BrightTALK Event
PRODID:-//BrightTALK//NONSGML BrightTALK Event Calendar//EN
CALSCALE:GREGORIAN
METHOD:REQUEST
BEGIN:VEVENT
UID:https://www.brighttalk.com/webcast/18657/656685
DTSTAMP:20251104T054238Z
ORGANIZER:MAILTO:noreply@brighttalk.com
LOCATION:BrightTALK
URL:https://www.brighttalk.com/webcast/18657/656685?utm_campaign=commu
 nication_reminder_starting_now_registrants&utm_medium=calendar&utm_sou
 rce=brighttalk-transact
DTSTART:20260603T050000Z
DTEND:20260603T055936Z
SUMMARY:Live webcast: Unreliable AI: Addressing the Cybersecurity Risk
 s of LLM-Based System
DESCRIPTION:Click here to attend: https://www.brighttalk.com/webcast/1
 8657/656685?utm_campaign=communication_reminder_starting_now_registran
 ts&utm_medium=calendar&utm_source=brighttalk-transact\n\nPresenter: Vl
 adislav Tushkanov - Research Development Group Manager | Machine Learn
 ing Technology |AI Research | Kaspersky\n\nAs AI systems based on larg
 e language models become more powerful and widespread, more cybersecur
 ity challenges emerge. From jailbreaks to indirect prompt injections, 
 they are vulnerable to a wide array of LLM-specific threats. However, 
 all these problems can be boiled down to one single issue: LLMs are pr
 obabilistic algorithms that are inherently unreliable, just like any o
 ther ML system. Does it mean they cannot be useful? Absolutely not! In
  this talk, we will discuss the challenges of secure and reliable LLM-
 based applications and the way to make them safer and more aligned wit
 h your business goals.
SEQUENCE:1780461968
END:VEVENT
END:VCALENDAR