DeepAI AI Chat
Log In Sign Up

Tightened Convex Relaxations for Neural Network Robustness Certification

by   Brendon G. Anderson, et al.
berkeley college

In this paper, we consider the problem of certifying the robustness of neural networks to perturbed and adversarial input data. Such certification is imperative for the application of neural networks in safety-critical decision-making and control systems. Certification techniques using convex optimization have been proposed, but they often suffer from relaxation errors that void the certificate. Our work exploits the structure of ReLU networks to improve relaxation errors through a novel partition-based certification procedure. The proposed method is proven to tighten existing linear programming relaxations, and asymptotically achieves zero relaxation error as the partition is made finer. We develop a finite partition that attains zero relaxation error and use the result to derive a tractable partitioning scheme that minimizes the worst-case relaxation error. Experiments using real data show that the partitioning procedure is able to issue robustness certificates in cases where prior methods fail. Consequently, partition-based certification procedures are found to provide an intuitive, effective, and theoretically justified method for tightening existing convex relaxation techniques.


page 1

page 2

page 3

page 4


Partition-Based Convex Relaxations for Certifying the Robustness of ReLU Neural Networks

In this paper, we study certifying the robustness of ReLU neural network...

Strengthened SDP Verification of Neural Network Robustness via Non-Convex Cuts

There have been major advances on the design of neural networks, but sti...

Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding

The robustness of deep neural networks has received significant interest...

Optimality Bounds for a Variational Relaxation of the Image Partitioning Problem

We consider a variational convex relaxation of a class of optimal partit...

Partition-based formulations for mixed-integer optimization of trained ReLU neural networks

This paper introduces a class of mixed-integer formulations for trained ...

Fastened CROWN: Tightened Neural Network Robustness Certificates

The rapid growth of deep learning applications in real life is accompani...

A Unified View of SDP-based Neural Network Verification through Completely Positive Programming

Verifying that input-output relationships of a neural network conform to...