Role of Optimizer on Network Fine-tuning for Adversarial Robustness (Student Abstract)

Authors

  • Akshay Agarwal IIIT-Delhi, India
  • Mayank Vatsa IIT Jodhpur, India
  • Richa Singh IIT Jodhpur, India

DOI:

https://doi.org/10.1609/aaai.v35i18.17869

Keywords:

Adversarial Robustness, COmputer Vision, CNN, Object Recognition

Abstract

The solutions proposed in the literature for adversarial robustness are either not effective against the challenging gradient-based attacks or are computationally demanding, such as adversarial training. Adversarial training or network training based data augmentation shows the potential to increase the adversarial robustness. While the training seems compelling, it is not feasible for resource-constrained institutions, especially academia, to train the network from scratch multiple times. The two fold contributions are: (i) providing an effective solution against white-box adversarial attacks via network fine-tuning steps and (ii) observing the role of different optimizers towards robustness. Extensive experiments are performed on a range of databases, including Fashion-MNIST and a subset of ImageNet. It is found that the few steps of network fine-tuning effectively increases the robustness of both shallow and deep architectures. To know other interesting observations, especially regarding the role of the optimizer, refer to the paper.

Downloads

Published

2021-05-18

How to Cite

Agarwal, A., Vatsa, M., & Singh, R. (2021). Role of Optimizer on Network Fine-tuning for Adversarial Robustness (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 15745-15746. https://doi.org/10.1609/aaai.v35i18.17869

Issue

Section

AAAI Student Abstract and Poster Program