用Mixed Integer Programming做神经网络的鲁棒性验证

Evaluating Robustness of Neural Networks with Mixed Integer Programming

 

# Remarks

Conference: ICLR 2019

Full Paper: https://groups.csail.mit.edu/robotics-center/public_papers/Tjeng17.pdf

 

# Abstract

Neural networks trained only to optimize for training accuracy can often be fooled by adversarial examples—slightly perturbed inputs misclassified with high confidence. The verification of networks enables us to gauge their vulnerability to such adversarial examples. We formulate the verification of piecewise-linear neural networks as a mixed-integer program. On a representative task of finding minimum adversarial distortions, our verifier is two to three orders of magnitude quicker than the state-of-the-art. We achieve this computational speedup via tight formulations for non-linearities, as well as a novel resolve