Sun 20 Oct 2024 16:30 - 17:00 at San Gabriel - Machine Learning and Neural networks Chair(s): Marco Campion

We develop a declarative DSL -ConstraintFlow- that can be used to specify Abstract Interpretation-based DNN certifiers. In ConstraintFlow, programmers can easily define various existing and new abstract domains and transformers, all within just a few 10s of Lines of Code as opposed to 1000s of LOCs of existing libraries. We provide lightweight automatic verification, which can be used to ensure the over-approximation-based soundness of the certifier code written in ConstraintFlow for arbitrary (but bounded) DNN architectures. Using this automated verification procedure, for the first time, we can verify the soundness of state-of-the-art DNN certifiers for arbitrary DNN architectures, all within a few minutes.

Sun 20 Oct

Displayed time zone: Pacific Time (US & Canada) change

16:00 - 17:30
Machine Learning and Neural networksSAS at San Gabriel
Chair(s): Marco Campion INRIA & École Normale Supérieure | Université PSL
16:00
30m
Full-paper
Abstract Interpretation of ReLU Neural Networks with Optimizable Polynomial Relaxations
SAS
Philipp Kern Karlsruhe Institute of Technology (KIT), Carsten Sinz Karlsruhe Institute of Technology
Pre-print
16:30
30m
Short-paper
ConstraintFlow: A DSL for Specification and Verification of Neural Network Analyses (NEAT paper)
SAS
Avaljot Singh UIUC, Yasmin Sarita Cornell University, Charith Mendis University of Illinois at Urbana-Champaign, Gagandeep Singh University of Illinois at Urbana-Champaign; VMware Research
Pre-print