BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//NextToU//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:b478fb20-217b-4ede-a6e6-1d4a1149a2e0@nexttoyou
DTSTAMP:20261105T155945Z
DTSTART:20261106T163000Z
DTEND:20261106T173000Z
SUMMARY:CIS Seminar Series 2026 - Ruzica Piskac\, PhD- Yale University
LOCATION:Kirkbride Lecture Hall 204\, Kirkbride Lecture Hall\, University 
 of Delaware\, Newark\, DE 19716\, USA
DESCRIPTION:Privacy-Preserving Automated Reasoning: From Program Verificat
 ion to Private AI Guardrails\n\nABSTRACT\nAs AI systems become increasing
 ly capable and autonomous\, ensuring that they behave correctly\, respect
  policies\, and protect sensitive information is a fundamental challenge.
  Formal methods and automated reasoning provide powerful tools for verify
 ing correctness\, while cryptographic techniques enable verification with
 out revealing sensitive information. In this talk\, I will present our on
 -going research on privacy-preserving automated reasoning.\nI will first 
 outline the framework for privacy-preserving program verification. Progra
 m verification provides stronger guarantees of correctness than standard 
 testing. The verification process takes a program as input and derives a 
 mathematical formula. Proving that the program is correct then reduces to
  establishing that this derived formula is unsatisfiable. Traditionally\,
  automated reasoning tools can determine unsatisfiability automatically\,
  and modern solvers can also produce proofs of unsatisfiability. However\
 , these techniques typically rely on the proof and the underlying code be
 ing publicly available\, which may not be desirable in certain applicatio
 ns. I will show how to address this challenge. We initially developed a p
 rotocol for validating the unsatisfiability of Boolean formulas in privac
 y-preserving settings. Building on these results\, we developed ZKSMT\, a
  virtual machine for validating unsatisfiability results produced \n\nhtt
 p://next-to-u.app/events/b478fb20-217b-4ede-a6e6-1d4a1149a2e0
URL:http://next-to-u.app/events/b478fb20-217b-4ede-a6e6-1d4a1149a2e0
END:VEVENT
END:VCALENDAR