Scalable Verification of Quantized Neural Networks (Technical Report)

by   Thomas A. Henzinger, et al.

Formal verification of neural networks is an active topic of research, and recent advances have significantly increased the size of the networks that verification tools can handle. However, most methods are designed for verification of an idealized model of the actual network which works over real arithmetic and ignores rounding imprecisions. This idealization is in stark contrast to network quantization, which is a technique that trades numerical precision for computational efficiency and is, therefore, often applied in practice. Neglecting rounding errors of such low-bit quantized neural networks has been shown to lead to wrong conclusions about the network's correctness. Thus, the desired approach for verifying quantized neural networks would be one that takes these rounding errors into account. In this paper, we show that verifying the bit-exact implementation of quantized neural networks with bit-vector specifications is PSPACE-hard, even though verifying idealized real-valued networks and satisfiability of bit-vector specifications alone are each in NP. Furthermore, we explore several practical heuristics toward closing the complexity gap between idealized and bit-exact verification. In particular, we propose three techniques for making SMT-based verification of quantized neural networks more scalable. Our experiments demonstrate that our proposed methods allow a speedup of up to three orders of magnitude over existing approaches.



There are no comments yet.


page 1

page 2

page 3

page 4


Searching for Low-Bit Weights in Quantized Neural Networks

Quantized neural networks with low-bit weights and activations are attra...

QNNVerifier: A Tool for Verifying Neural Networks using SMT-Based Model Checking

QNNVerifier is the first open-source tool for verifying implementations ...

Efficient Exact Verification of Binarized Neural Networks

Concerned with the reliability of neural networks, researchers have deve...

Verifying Probabilistic Specifications with Functional Lagrangians

We propose a general framework for verifying input-output specifications...

Online Verification of Deep Neural Networks under Domain or Weight Shift

Although neural networks are widely used, it remains challenging to form...

A Precise and Expressive Lattice-theoretical Framework for Efficient Network Verification

Network verification promises to detect errors, such as black holes and ...

BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networks

Verifying and explaining the behavior of neural networks is becoming inc...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.