Verification of Neural Networks (Lecture Notes)

Benedikt Bollig

cs.LOApr 28, 2026

Verification of Neural Networks (Lecture Notes)

Authors: Benedikt Bollig

Organizations: Universit´e Paris-Saclay, CNRS, ENS Paris-Saclay, LMF

Abstract

These lecture notes provide an introduction to the verification of neural networks from a theoretical perspective. We discuss feed-forward neural networks, recurrent neural networks, attention mechanisms, and transformers, together with specification languages and algorithmic verification techniques.

Explore similar work

Learning Lookahead Lemmas for Neural Network Verification
Jul 31, 2026Liam Davis, Haoze WuNeural Network Verification Neural Network
The Complexity of Verifying Feedforward Neural Networks in Quantised Settings
May 28, 2026Eric Alsmann, Martin Lange, Marco SälzerNeural Network Verification Quantum Neural Networks
VNN-LIB 2.0: Rigorous Foundations for Neural Network Verification
May 8, 2026Ann Roy, Allen Antony, Andrea Gimelli +1Neural Network Verification Formal Verification

Jul 31, 2026 · cs.LGJ/K move · Enter open · S save

Learning Lookahead Lemmas for Neural Network Verification

Liam Davis, Haoze Wu

Amherst College

State-of-the-art neural network verifiers use the branch-and-bound procedure as their core solving mechanism. We introduce an inprocessing framework for neural network verification driven by the lookahead procedure. Under this framework, lookahead derives new lemmas over the phases of unstable ReLUs, which are collected into an implication graph that is used to prune the search space and vivify boolean cuts. We instantiate the framework in two state-of-the-art verifiers, Marabou and

α

β

-CROWN, and demonstrate that it improves performance in both, proving up to 34% more instances unsatisfiable.

Neural Network Verification Neural Network Lookahead

Open paper Ask about it PDF

Abstract

Explore similar work

Learning Lookahead Lemmas for Neural Network Verification

The Complexity of Verifying Feedforward Neural Networks in Quantised Settings

VNN-LIB 2.0: Rigorous Foundations for Neural Network Verification