Provably Secure: Math Against Superintelligent Hackers

Worry is growing around AI agents escaping containment and acting against the interests of the organizations that built them. The latest LLMs are also finding cybersecurity vulnerabilities in important software at an alarming pace. Against this backdrop, join the Social and Ethical Responsibilities of Computing on November 17 for a panel discussion exploring whether mathematical proofs could work to thwart superintelligent cyberattackers. Bringing together experts from academia, government, and industry, the conversation will survey an old computer-science technique with new promise: formal verification, mathematical proof about the behavior of programs. Can such proofs be applied to important computing infrastructure, to guarantee agent containment and find all security bugs of certain kinds, future-proofing against more-powerful LLMs? The panel will be moderated by Adam Chlipala, Arthur J. Conner (1888) Professor of Computer Science at MIT, and will feature Byron Cook, vice president and distinguished scientist at Amazon Web Services; Noah Evans, principal member of technical staff at Draper; and Armando Solar-Lezama, Distinguished Professor of Computing at MIT.