DeepAI AI Chat
Log In Sign Up

Data-Driven Assessment of Deep Neural Networks with Random Input Uncertainty

by   Brendon G. Anderson, et al.

When using deep neural networks to operate safety-critical systems, assessing the sensitivity of the network outputs when subject to uncertain inputs is of paramount importance. Such assessment is commonly done using reachability analysis or robustness certification. However, certification techniques typically ignore localization information, while reachable set methods can fail to issue robustness guarantees. Furthermore, many advanced methods are either computationally intractable in practice or restricted to very specific models. In this paper, we develop a data-driven optimization-based method capable of simultaneously certifying the safety of network outputs and localizing them. The proposed method provides a unified assessment framework, as it subsumes state-of-the-art reachability analysis and robustness certification. The method applies to deep neural networks of all sizes and structures, and to random input uncertainty with a general distribution. We develop sufficient conditions for the convexity of the underlying optimization, and for the number of data samples to certify and localize the outputs with overwhelming probability. We experimentally demonstrate the efficacy and tractability of the method on a deep ReLU network.


page 7

page 8


Certifying Neural Network Robustness to Random Input Noise from Samples

Methods to certify the robustness of neural networks in the presence of ...

Vertex-based reachability analysis for verifying ReLU deep neural networks

Neural networks achieved high performance over different tasks, i.e. ima...

Safety Verification for Neural Networks Based on Set-boundary Analysis

Neural networks (NNs) are increasingly applied in safety-critical system...

Reachability Analysis of Deep Neural Networks with Provable Guarantees

Verifying correctness of deep neural networks (DNNs) is challenging. We ...

Towards the Unification and Data-Driven Synthesis of Autonomous Vehicle Safety Concepts

As safety-critical autonomous vehicles (AVs) will soon become pervasive ...

Robust Optimization Framework for Training Shallow Neural Networks Using Reachability Method

In this paper, a robust optimization framework is developed to train sha...

Robustness Analysis of Neural Networks via Efficient Partitioning: Theory and Applications in Control Systems

Neural networks (NNs) are now routinely implemented on systems that must...