Static deep neural network analysis for robustness

Abstract

This work studies the static structure of deep neural network models using white box based approach and utilizes that knowledge to find the susceptible classes which can be misclassified easily. With the knowledge of susceptible classes, our work has proposed to retrain the model for those classes to achieve increased robustness. Our preliminary result has been evaluated on MNIST, F-MNIST, and CIFAR-10 (ImageNet and ResNet-32 model) based datasets and have been compared with two state-of-the-art detectors.

Publication
The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) (Aug. 2019)
Avatar
Rangeet Pan
Research Assistant

My research interests include distributed robotics, mobile computing and programmable matter.