BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//NextToU//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:505ed571-3f82-46fd-bf5c-f2f291e9118f@nexttoyou
DTSTAMP:20261106T180120Z
DTSTART:20261117T213000Z
DTEND:20261117T233000Z
SUMMARY:Provably Secure: Math Against Superintelligent Hackers
LOCATION:Building 32 155\, 32 VASSAR ST\, Cambridge\, MA 02139
DESCRIPTION:Worry is growing around AI agents escaping containment and act
 ing against the interests of the organizations that built them. The lates
 t LLMs are also finding cybersecurity vulnerabilities in important softwa
 re at an alarming pace.\n\nAgainst this backdrop\, join the Social and Et
 hical Responsibilities of Computing on November 17 for a panel discussion
  exploring whether mathematical proofs could work to thwart superintellig
 ent cyberattackers.\n\nBringing together experts from academia\, governme
 nt\, and industry\, the conversation will survey an old computer-science 
 technique with new promise: formal verification\, mathematical proof abou
 t the behavior of programs. Can such proofs be applied to important compu
 ting infrastructure\, to guarantee agent containment and find all securit
 y bugs of certain kinds\, future-proofing against more-powerful LLMs?\n\n
 The panel will be moderated by Adam Chlipala\, Arthur J. Conner (1888) Pr
 ofessor of Computer Science at MIT\, and will feature Byron Cook\, vice p
 resident and distinguished scientist at Amazon Web Services\; Noah Evans\
 , principal member of technical staff at Draper\; and Armando Solar-Lezam
 a\, Distinguished Professor of Computing at MIT.\n\nhttp://next-to-u.app/
 events/505ed571-3f82-46fd-bf5c-f2f291e9118f
URL:http://next-to-u.app/events/505ed571-3f82-46fd-bf5c-f2f291e9118f
END:VEVENT
END:VCALENDAR