Towards Proving the Adversarial Robustness of Deep Neural Networks

09/08/2017
by   Guy Katz, et al.
0

Autonomous vehicles are highly complex systems, required to function reliably in a wide variety of situations. Manually crafting software controllers for these vehicles is difficult, but there has been some success in using deep neural networks generated using machine-learning. However, deep neural networks are opaque to human engineers, rendering their correctness very difficult to prove manually; and existing automated techniques, which were not designed to operate on neural networks, fail to scale to large systems. This paper focuses on proving the adversarial robustness of deep neural networks, i.e. proving that small perturbations to a correctly-classified input to the network cannot cause it to be misclassified. We describe some of our recent and ongoing work on verifying the adversarial robustness of networks, and discuss some of the open questions we have encountered and how they might be addressed.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/24/2019

A Formalization of Robustness for Deep Neural Networks

Deep neural networks have been shown to lack robustness to small input p...
research
04/13/2020

Adversarial robustness guarantees for random deep neural networks

The reliability of most deep learning algorithms is fundamentally challe...
research
10/02/2019

Supply-Power-Constrained Cable Capacity Maximization Using Deep Neural Networks

We experimentally achieve a 19 power in a 12-span link by eliminating ga...
research
09/03/2018

Have You Stolen My Model? Evasion Attacks Against Deep Neural Network Watermarking Techniques

Deep neural networks have had enormous impact on various domains of comp...
research
10/18/2018

Compositional Verification for Autonomous Systems with Deep Learning Components

As autonomy becomes prevalent in many applications, ranging from recomme...
research
11/10/2022

Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts

Self-trained autonomous agents developed using machine learning are show...
research
12/22/2020

Limitations of Deep Neural Networks: a discussion of G. Marcus' critical appraisal of deep learning

Deep neural networks have triggered a revolution in artificial intellige...

Please sign up or login with your details

Forgot password? Click here to reset