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
research
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...
research
01/27/2023

Vertex-based reachability analysis for verifying ReLU deep neural networks

Neural networks achieved high performance over different tasks, i.e. ima...
research
09/29/2017

Ground-Truth Adversarial Examples

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

Safety Verification of Deep Neural Networks

Deep neural networks have achieved impressive experimental results in im...
research
05/31/2023

Optimal Sets and Solution Paths of ReLU Networks

We develop an analytical framework to characterize the set of optimal Re...
research
02/23/2018

Verifying Controllers Against Adversarial Examples with Bayesian Optimization

Recent successes in reinforcement learning have lead to the development ...
research
03/19/2020

Automated Formal Synthesis of Lyapunov Neural Networks

We propose an automated and sound technique to synthesize provably corre...

Please sign up or login with your details

Forgot password? Click here to reset