BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CFP.DEV//CFP.DEV shortcodes//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Voxxed Days Ticino 2026
X-WR-RELCALID:c426493a-54d4-472b-b975-6f3aaa7163fa
X-WR-TIMEZONE:Europe/Zurich
BEGIN:VEVENT
UID:cfp-1151-8663@cfp.dev
DTSTAMP:20260920T122430Z
SEQUENCE:0
STATUS:CONFIRMED
DTSTART:20260206T111000Z
DTEND:20260206T113000Z
SUMMARY:Why Security Matters: The Risks of Agentic AI and How to Mitigate T
 hem
DESCRIPTION:The hype of AI Agents is in full swing\, with Anthropic&#39\;s 
 Model Context Protocol (MCP) being the highly popular\, de facto standard 
 to connect agents with external tools to access files\, networks\, and API
 s. Here\, unfortunately\, security has been left once again as an aftertho
 ught. Ever since LLMs were given the possibility to interact with your com
 puter and environment via tool calls and MCP\, not much has been done abou
 t security. So\, how can we secure AI agent-based systems before we end up
  in a security nightmare?In this session for AI-\, security-\, and softwar
 e-engineers\, we shed some light on the security challenges of agentic AI 
 systems and how to mitigate them. We show how the application of a permiss
 ion-based access control mechanism can encapsulate MCP servers that are ot
 herwise executed with full privileges. We discuss how our solution comes a
 t little to no performance cost and is compatible with the current impleme
 ntations of MCP servers\, allowing for easy adoption.\nSpeakers: Christoph
  Bühler\nTrack: Security
URL:https://vdt26.voxxeddays.ch/talk/why-security-matters-the-risks-of-agen
 tic-ai-and-how-to-mitigate-them/
LOCATION:Room B1\nPalazzo dei Congressi\nLugano\, Switzerland
CATEGORIES:Security
END:VEVENT
END:VCALENDAR