Toward Scalable Verification for Safety-Critical Deep Networks

01/18/2018
by   Lindsey Kuper, et al.
0

The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability. Formal verification can address these concerns by guaranteeing that a deep learning system operates as intended, but the state-of-the-art is limited to small systems. In this work-in-progress report we give an overview of our work on mitigating this difficulty, by pursuing two complementary directions: devising scalable verification techniques, and identifying design choices that result in deep learning systems that are more amenable to verification.

READ FULL TEXT

page 1

page 2

page 3

research
04/01/2019

Open Problems in Engineering Machine Learning Systems and the Quality Model

Fatal accidents are a major issue hindering the wide acceptance of safet...
research
01/22/2020

Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Tasks

Deep learning methods are widely regarded as indispensable when it comes...
research
04/26/2021

Fast Falsification of Neural Networks using Property Directed Testing

Neural networks are now extensively used in perception, prediction and c...
research
05/03/2019

A New Hierarchical Software Architecture Towards Safety-Critical Aspects of a Drone System

In this paper, a new hierarchical software architecture is proposed to i...
research
03/02/2020

Towards Probability-based Safety Verification of Systems with Components from Machine Learning

Machine learning (ML) has recently created many new success stories. Hen...
research
12/06/2022

veriFIRE: Verifying an Industrial, Learning-Based Wildfire Detection System

In this short paper, we present our ongoing work on the veriFIRE project...
research
12/05/2017

Towards Practical Verification of Machine Learning: The Case of Computer Vision Systems

Due to the increasing usage of machine learning (ML) techniques in secur...

Please sign up or login with your details

Forgot password? Click here to reset