ml-lab / neuralnetworkverification_globalrobustness

Verification of Neural Networks: Specifying Global Robustness using Generative Models

We present experiments exploring the notions of global correctness and global robustness defined in our research paper:

Nathanaël Fijalkow and Mohit Kumar Gupta

Verification of Neural Networks: Specifying Global Robustness using Generative Models

arXiv link

The experiments are in Jupter notebook format:

• Random walk
• Analysis of an image classifier using a generative model
• Evaluating the global correctness
• Searching for Realistic Adversarial Examples: black-box approach
• Searching for Realistic Adversarial Examples: white-box approach
• Dependence on the generative model: disjoint training sets

All experiments use Tensorflow, and pre-trained models can be used (see /Models).