Global Optimization of Objective Functions Represented by ReLU Networks

10/07/2020
by   Christopher A. Strong, et al.
0

Neural networks (NN) learn complex non-convex functions, making them desirable solutions in many contexts. Applying NNs to safety-critical tasks demands formal guarantees about their behavior. Recently, a myriad of verification solutions for NNs emerged using reachability, optimization, and search based techniques. Particularly interesting are adversarial examples, which reveal ways the network can fail. They are widely generated using incomplete methods, such as local optimization, which cannot guarantee optimality. We propose strategies to extend existing verifiers to provide provably optimal adversarial examples. Naive approaches combine bisection search with an off-the-shelf verifier, resulting in many expensive calls to the verifier. Instead, our proposed approach yields tightly integrated optimizers, achieving better runtime performance. We extend Marabou, an SMT-based verifier, and compare it with the bisection based approach and MIPVerify, an optimization based verifier.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 21

02/03/2017

Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks

Deep neural networks have emerged as a widely used and effective means f...
04/24/2018

Towards Dependable Deep Convolutional Neural Networks (CNNs) with Out-distribution Learning

Detection and rejection of adversarial examples in security sensitive an...
09/29/2017

Ground-Truth Adversarial Examples

The ability to deploy neural networks in real-world, safety-critical sys...
10/21/2016

Safety Verification of Deep Neural Networks

Deep neural networks have achieved impressive experimental results in im...
02/23/2018

Verifying Controllers Against Adversarial Examples with Bayesian Optimization

Recent successes in reinforcement learning have lead to the development ...
11/02/2017

Provable defenses against adversarial examples via the convex outer adversarial polytope

We propose a method to learn deep ReLU-based classifiers that are provab...
03/19/2020

Automated Formal Synthesis of Lyapunov Neural Networks

We propose an automated and sound technique to synthesize provably corre...
This week in AI

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