BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:9097@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20260529T160000
DTEND;TZID=Europe/Paris:20260529T170000
DTSTAMP:20260508T134231Z
URL:https://www.i2m.univ-amu.fr/evenements/ai4crypto-training-small-ai-mod
 els-to-solve-hard-math-problems/
SUMMARY:Kristin Lauter (Meta): AI4Crypto: training small AI models to solve
  hard math problems
DESCRIPTION:Kristin Lauter: AI is taking off and we could say we are living
  in “the AI Era”.  Progress in AI today is based on mathematics and s
 tatistics tools to train machine learning models on large amounts of data\
 , to accomplish various prediction tasks like classification.  \nThis ta
 lk will explain five years of work on AI4Crypto\, where we train AI models
  to attack Post Quantum Cryptography (PQC) schemes based on lattices.  Th
 is work is a case study in training small ML models to solve hard math pro
 blems in practice.  Our AI4Crypto project has developed AI models capable
  of recovering secrets in post-quantum cryptosystems (PQC).  The standard
 ized PQC systems were designed to be secure against a quantum computer\, b
 ut are not necessarily safe against advanced AI!  Understanding the conc
 rete security of these standardized PQC schemes is important for the futur
 e of e-commerce and internet security.  So instead of saying that we are 
 living in a “Post-Quantum” era\, we should say that we are living in a
  “Post-AI” era!
CATEGORIES:Colloquium
LOCATION:Saint-Charles - FRUMAM  (2ème étage)\, 3 Place Victor Hugo\, Mar
 seille\, 13003\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=3 Place Victor Hugo\, Marse
 ille\, 13003\, France;X-APPLE-RADIUS=100;X-TITLE=Saint-Charles - FRUMAM  (
 2ème étage):geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:DAYLIGHT
DTSTART:20260329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR