4 papers
Neuro-Inspired Deep Neural Networks with Sparse, Strong Activations
Metehan Cekic, Can Bakiskan, Upamanyu Madhow
While end-to-end training of Deep Neural Networks (DNNs) yields state of the art performance in an increasing array of applications, it does not provide insight into, or control ov…
Sparse Coding Frontend for Robust Neural Networks
Can Bakiskan, Metehan Cekic, Ahmet Dundar Sezer +1
Deep Neural Networks are known to be vulnerable to small, adversarially crafted, perturbations. The current most effective defense methods against these adversarial attacks are var…
A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations
Can Bakiskan, Metehan Cekic, Ahmet Dundar Sezer +1
Deep Neural Networks (DNNs) are vulnerable to adversarial attacks: carefully constructed perturbations to an image can seriously impair classification accuracy, while being imperce…
Polarizing Front Ends for Robust CNNs
Can Bakiskan, Soorya Gopalakrishnan, Metehan Cekic +2
The vulnerability of deep neural networks to small, adversarially designed perturbations can be attributed to their "excessive linearity." In this paper, we propose a bottom-up str…