Debona: Decoupled Boundary Network Analysis for Tighter Bounds and Faster Adversarial Robustness Proofs

by   Christopher Brix, et al.

Neural networks are commonly used in safety-critical real-world applications. Unfortunately, the predicted output is often highly sensitive to small, and possibly imperceptible, changes to the input data. Proving that either no such adversarial examples exist, or providing a concrete instance, is therefore crucial to ensure safe applications. As enumerating and testing all potential adversarial examples is computationally infeasible, verification techniques have been developed to provide mathematically sound proofs of their absence using overestimations of the network activations. We propose an improved technique for computing tight upper and lower bounds of these node values, based on increased flexibility gained by computing both bounds independently of each other. Furthermore, we gain an additional improvement by re-implementing part of the original state-of-the-art software "Neurify", leading to a faster analysis. Combined, these adaptations reduce the necessary runtime by up to 78 too complex. Finally, we provide proofs for tight upper and lower bounds on max-pooling layers in convolutional networks. To ensure widespread usability, we open source our implementation "Debona", featuring both the implementation specific enhancements as well as the refined boundary computation for faster and more exact results.


page 1

page 2

page 3

page 4


Computing Upper and Lower Bounds on Likelihoods in Intractable Networks

We present deterministic techniques for computing upper and lower bounds...

Alternation-Trading Proofs, Linear Programming, and Lower Bounds

A fertile area of recent research has demonstrated concrete polynomial t...

Robustness Certificates Against Adversarial Examples for ReLU Networks

While neural networks have achieved high performance in different learni...

A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees

Despite the improved accuracy of deep neural networks, the discovery of ...

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...

The Stretch Factor of Hexagon-Delaunay Triangulations

The problem of computing the exact stretch factor (i.e., the tight bound...

Code Repositories


Decoupled Boundary Network Analysis for Tighter Bounds and Faster Adversarial Robustness Proofs

view repo

Please sign up or login with your details

Forgot password? Click here to reset