Can Bakiskan

According to our database, Can Bakiskan authored at least 7 papers between 2020 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2022

Structural Defense Techniques in Adversarial Machine Learning

Can Bakiskan

PhD thesis, 2022

Towards robust, interpretable neural networks via Hebbian/anti-Hebbian learning: A software framework for training with feature-based costs.

Metehan Cekic, Can Bakiskan, Upamanyu Madhow

Softw. Impacts, 2022

Neuro-Inspired Deep Neural Networks with Sparse, Strong Activations.

Metehan Cekic, Can Bakiskan, Upamanyu Madhow

Proceedings of the 2022 IEEE International Conference on Image Processing, 2022

2021

Sparse Coding Frontend for Robust Neural Networks.

Can Bakiskan, Metehan Cekic, Ahmet Dundar Sezer, Upamanyu Madhow

CoRR, 2021

A Neuro-Inspired Autoencoding Defense Against Adversarial Attacks.

Can Bakiskan, Metehan Cekic, Ahmet Dundar Sezer, Upamanyu Madhow

Proceedings of the 2021 IEEE International Conference on Image Processing, 2021

2020

A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations.

Can Bakiskan, Metehan Cekic, Ahmet Dundar Sezer, Upamanyu Madhow

CoRR, 2020

Polarizing Front Ends for Robust Cnns.

Can Bakiskan, Soorya Gopalakrishnan, Metehan Cekic, Upamanyu Madhow, Ramtin Pedarsani

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020