Static deep neural network analysis for robustness
| Autor: | Rangeet Pan |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Artificial neural network
business.industry Computer science Detector 020207 software engineering Pattern recognition 02 engineering and technology Static structure Neural network analysis Robustness (computer science) 020204 information systems 0202 electrical engineering electronic engineering information engineering Artificial intelligence White box business MNIST database |
| Zdroj: | ESEC/SIGSOFT FSE |
| DOI: | 10.1145/3338906.3342502 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|