239 citations · 261 across the 5 of their papers we have counts for
4 papers · 1 filter
Robust Adversarial Learning via Sparsifying Front Ends
Soorya Gopalakrishnan, Zhinus Marzi, Metehan Cekic +2
It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks. In this paper, we take a bottom-up signal processing perspect…
On the information in spike timing: neural codes derived from polychronous groups
Zhinus Marzi, Joao Hespanha, Upamanyu Madhow
There is growing evidence regarding the importance of spike timing in neural information processing, with even a small number of spikes carrying information, but computational mode…
Combating Adversarial Attacks Using Sparse Representations
Soorya Gopalakrishnan, Zhinus Marzi, Upamanyu Madhow +1
It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks (DNNs). In this paper, we make the case that sparse representa…
Sparsity-based Defense against Adversarial Attacks on Linear Classifiers
Zhinus Marzi, Soorya Gopalakrishnan, Upamanyu Madhow +1
Deep neural networks represent the state of the art in machine learning in a growing number of fields, including vision, speech and natural language processing. However, recent wor…