survey arXiv Apr 28, 2026 · 23d ago
Benedikt Bollig · Université Paris-Saclay · CNRS +1 more
Theoretical introduction to formal verification techniques for neural networks including feed-forward, recurrent, attention, and transformer architectures
Input Manipulation Attack visionnlp
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.
cnn transformer rnn Université Paris-Saclay · CNRS · ENS Paris-Saclay
