LGAIPLSep 21, 2021

Introduction to Neural Network Verification

arXiv:2109.10317v2111 citations
AI Analysis

This work tackles the problem of ensuring reliability in neural networks for applications requiring high assurance, but it is incremental as it adapts existing verification ideas.

The paper addresses the fragility and surprising behaviors of deep neural networks by adapting foundational formal verification methods to provide formal guarantees on safety, security, correctness, or robustness.

Deep learning has transformed the way we think of software and what it can do. But deep neural networks are fragile and their behaviors are often surprising. In many settings, we need to provide formal guarantees on the safety, security, correctness, or robustness of neural networks. This book covers foundational ideas from formal verification and their adaptation to reasoning about neural networks and deep learning.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes