AI4Crypto: training small AI models to solve hard math problems
Kristin Lauter
Meta
https://ai.meta.com/people/786716476205590/kristin-e-lauter/
Date(s) : 29/05/2026 iCal
16h00 - 17h00
AI is taking off and we could say we are living in “the AI Era”. Progress in AI today is based on mathematics and statistics tools to train machine learning models on large amounts of data, to accomplish various prediction tasks like classification.
This talk will explain five years of work on AI4Crypto, where we train AI models to attack Post Quantum Cryptography (PQC) schemes based on lattices. This work is a case study in training small ML models to solve hard math problems in practice. Our AI4Crypto project has developed AI models capable of recovering secrets in post-quantum cryptosystems (PQC). The standardized PQC systems were designed to be secure against a quantum computer, but are not necessarily safe against advanced AI! Understanding the concrete security of these standardized PQC schemes is important for the future 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!
Emplacement
Saint-Charles - FRUMAM (2ème étage)
Catégories
