An Introduction to Neural Network Verification

A book by Aws Albarghouthi

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 in-progress book covers foundational ideas from formal verification and their adaptation to reasoning about neural networks and deep learning.

A full PDF is coming soon. The book has 3 parts. Parts 2 and 3 are disjoint; the reader may go directly from Part 1 to Part 3 without losing context.

Part I Neural networks and correctness

1. Neural networks and correctness
2. Neural networks as graphs
3. Correctness properties

Part II Constraint-based verification

4. Logic and satisfiability
5. Encodings of neural networks
6. DPLL modulo theories
7. Neural theory solvers

Part III Abstraction-based verification

8. Neural interval abstraction
9. Neural zonotope abstraction
10. Neural polyhedron abstraction
11. Verification with abstract interpretation
12. Abstract training of neural networks

13. Looking ahead

For comments, contact the author.
Please use the following to cite this book.
    title = {Verified Deep Learning},
    author = {Aws Albarghouthi},
    publisher = {},
    note = {\url{}},
    year = {2021}
Last updated