BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Chicago BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:CDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260831T021712Z UID:064995EF-061A-4735-A85A-A3311274F2DA DTSTART;TZID=America/Chicago:20261028T150000 DTEND;TZID=America/Chicago:20261028T160000 DESCRIPTION:Cybersecurity in the Age of AI Assistants: What Everyone Should Know\n\nAI assistants have shifted from answering questions to taking act ions on our behalf. They read messages\, handle requests\, and are increas ingly trusted to look things up\, decide\, and act. That shift quietly cha nges the security picture\, because an assistant that acts on what it read s can be given instructions by anyone whose text reaches it. The old lesso n applies in a new place: input from the outside world cannot be trusted\, and a system should never be permitted to do more than the task in front of it requires.\n\nThis session teaches the core ideas of cybersecurity by showing them fail and then hold\, live. Participants are given access to a purpose-built demonstration environment: a simulated customer support de sk where an AI assistant reads incoming tickets and can look up records\, issue credits\, and send messages. The room submits tickets\, and the disp lay shows everything the assistant received\, decided\, and did. Within mi nutes participants find that ordinary-looking requests can carry instructi ons that lead the assistant to disclose what it was told to protect or to take actions no customer should be able to trigger. The second half turns on the defenses one at a time (limiting what the assistant is connected to \, separating what it may read from what it may act on\, requiring a perso n to approve anything consequential\, and checking what it sends back out) \, and participants replay their own successful attempts to see which cont rols hold and which do not. The session connects this directly to everyday practice: what should never be entered into a chat window\, why these tec hniques are close relatives of the phishing messages everyone already know s to distrust\, and what to ask before trusting an AI tool with anything t hat matters.\n\nThe closing segment is written for students and early-care er attendees. It covers where the work in this field actually is\, includi ng security engineering\, testing and red-teaming AI systems\, privacy and data protection\, incident response\, and the growing governance and assu rance side\, along with what those roles look like day to day and how they differ from the general software and IT paths students are more often sho wn. It ends with concrete preparation advice: the fundamentals worth build ing first\, why curiosity about how systems break matters more than any si ngle tool\, how to gain real experience through open resources and competi tions\, and how IEEE membership\, student chapters\, and events like this one open the first doors.\n\nVirtual: https://events.vtools.ieee.org/m/575 010 LOCATION:Virtual: https://events.vtools.ieee.org/m/575010 ORGANIZER:robert.burke@ieee.org SEQUENCE:25 SUMMARY:R4 Workshop: Cybersecurity in the Age of AI Assistants: What Everyo ne Should Know URL;VALUE=URI:https://events.vtools.ieee.org/m/575010 X-ALT-DESC:Description: <br /><p>Cybersecurity in the Age of AI Assistants: What Everyone Should Know<br><br>AI assistants have shifted from answerin g questions to taking actions on our behalf. They read messages\, handle r equests\, and are increasingly trusted to look things up\, decide\, and ac t. That shift quietly changes the security picture\, because an assistant that acts on what it reads can be given instructions by anyone whose text reaches it. The old lesson applies in a new place: input from the outside world cannot be trusted\, and a system should never be permitted to do mor e than the task in front of it requires.<br><br>This session teaches the c ore ideas of cybersecurity by showing them fail and then hold\, live. Part icipants are given access to a purpose-built demonstration environment: a simulated customer support desk where an AI assistant reads incoming ticke ts and can look up records\, issue credits\, and send messages. The room s ubmits tickets\, and the display shows everything the assistant received\, decided\, and did. Within minutes participants find that ordinary-looking requests can carry instructions that lead the assistant to disclose what it was told to protect or to take actions no customer should be able to tr igger. The second half turns on the defenses one at a time (limiting what the assistant is connected to\, separating what it may read from what it m ay act on\, requiring a person to approve anything consequential\, and che cking what it sends back out)\, and participants replay their own successf ul attempts to see which controls hold and which do not. The session conne cts this directly to everyday practice: what should never be entered into a chat window\, why these techniques are close relatives of the phishing m essages everyone already knows to distrust\, and what to ask before trusti ng an AI tool with anything that matters.<br><br>The closing segment is wr itten for students and early-career attendees. It covers where the work in this field actually is\, including security engineering\, testing and red -teaming AI systems\, privacy and data protection\, incident response\, an d the growing governance and assurance side\, along with what those roles look like day to day and how they differ from the general software and IT paths students are more often shown. It ends with concrete preparation adv ice: the fundamentals worth building first\, why curiosity about how syste ms break matters more than any single tool\, how to gain real experience t hrough open resources and competitions\, and how IEEE membership\, student chapters\, and events like this one open the first doors.</p> END:VEVENT END:VCALENDAR