Follow
Metehan Cekic
Metehan Cekic
Applied Scientist, Amazon
Verified email at amazon.com - Homepage
Title
Cited by
Cited by
Year
Robust wireless fingerprinting via complex-valued neural networks
S Gopalakrishnan, M Cekic, U Madhow
2019 IEEE Global Communications Conference (GLOBECOM), 1-6, 2019
522019
Wireless fingerprinting via deep learning: The impact of confounding factors
M Cekic, S Gopalakrishnan, U Madhow
2021 55th Asilomar Conference on Signals, Systems, and Computers, 677-684, 2021
47*2021
Neuro-Inspired Deep Neural Networks with Sparse, Strong Activations
M Cekic, C Bakiskan, U Madhow
2022 IEEE International Conference on Image Processing (ICIP), 2022
102022
Robust adversarial learning via sparsifying front ends
S Gopalakrishnan, Z Marzi, M Cekic, U Madhow, R Pedarsani
arXiv preprint arXiv:1810.10625, 2018
72018
Early layers are more important for adversarial robustness
C Bakiskan, M Cekic, U Madhow
ICLR 2022 Workshop on New Frontiers in Adversarial Machine Learning, 2022
62022
Polarizing front ends for robust CNNs
C Bakiskan, S Gopalakrishnan, M Cekic, U Madhow, R Pedarsani
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
52020
Towards robust, interpretable neural networks via Hebbian/anti-Hebbian learning: A software framework for training with feature-based costs
M Cekic, C Bakiskan, U Madhow
Software Impacts 13, 100347, 2022
42022
Self-supervised speaker recognition training using human-machine dialogues
M Cekic, R Li, Z Chen, Y Yang, A Stolcke, U Madhow
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
42022
PEAVS: Perceptual Evaluation of Audio-Visual Synchrony Grounded in Viewers' Opinion Scores
L Goncalves, P Mathur, C Lavania, M Cekic, M Federico, KJ Han
arXiv preprint arXiv:2404.07336, 2024
2024
Robust Learning Techniques for Deep Neural Networks
M Cekic
University of California, Santa Barbara, 2022
2022
Layerwise Hebbian/anti-Hebbian (HaH) Learning In Deep Networks: A Neuro-inspired Approach To Robustness
M Cekic, C Bakiskan, U Madhow
ICML 2022 Workshop on New Frontiers in Adversarial Machine Learning, 2022
2022
A Neuro-Inspired Autoencoding Defense Against Adversarial Attacks
C Bakiskan, M Cekic, AD Sezer, U Madhow
2021 IEEE International Conference on Image Processing (ICIP), 3922-3926, 2021
2021
Sparse Coding Frontend for Robust Neural Networks
C Bakiskan, M Cekic, AD Sezer, U Madhow
International Conference on Learning Representations (ICLR), Workshop on …, 2021
2021
A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations
C Bakiskan, M Cekic, AD Sezer, U Madhow
arXiv preprint arXiv:2011.10867, 2020
2020
The system can't perform the operation now. Try again later.
Articles 1–14