Metehan Cekic

Metehan received his B.S. degrees in Electrical and Electronics Engineering and Physics from Bogazici University, Istanbul, in 2017 and M.S degree in Electrical and Computer Engineering from the University of California, Santa Barbara, in 2019. 

Homepage Linkedin Scholar CV

Email: metehancekic [at] ucsb [dot] edu

Research:

  • Radio Frequency Machine Learning (RFML)
  • Adversarial Machine Learning

Related Publications

Metehan Cekic*, Can Bakiskan*, Upamanyu Madhow , "Neuro-Inspired Deep Neural Networks with Sparse, Strong Activations", 29th IEEE International Conference on Image Processing (IEEE ICIP 2022)
Metehan Cekic*, Can Bakiskan*, Upamanyu Madhow, "Layerwise Hebbian/anti-Hebbian (HaH) Learning In Deep Networks: A Neuro-inspired Approach To Robustness", International Conference on Machine Learning (ICML) 2022 Workshop – New Frontiers in Adversarial Machine Learning
Metehan Cekic, Can Bakiskan, Upamanyu Madhow, "Towards Robust, Interpretable Neural Networks via Hebbian/anti-Hebbian Learning: A Software Framework for Training with Feature-Based Costs", Software Impacts Journal (2022)
Can Bakiskan, Metehan Cekic, Upamanyu Madhow, "Early Layers Are More Important For Adversarial Robustness", International Conference on Machine Learning (ICML) 2022 Workshop – New Frontiers in Adversarial Machine Learning
Metehan Cekic, Ruirui Li, Zeya Chen, Yuguang Yang, Andreas Stolcke, Upamanyu Madhow, "Self-Supervised Speaker Recognition Training using Human-Machine Dialogues", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022
Metehan Cekic*, Soorya Gopalakrishnan*, Upamanyu Madhow, "Wireless Fingerprinting via Deep Learning: The Impact of Confounding Factors", 55th Asilomar Conference on Signals, Systems and Computers
Can Bakiskan, Metehan Cekic, Ahmet Dundar Sezer, Upamanyu Madhow, "Sparse Coding Frontend for Robust Neural Networks ", ICLR 2021 Workshop on Security and Safety in Machine Learning Systems
Can Bakiskan, Metehan Cekic, Ahmet Dundar Sezer, Upamanyu Madhow, "A Neuro-Inspired Autoencoding Defense Against Adversarial Perturbations", arXiv preprint
Can Bakiskan, Metehan Cekic, Ahmet Dundar Sezer, Upamanyu Madhow, "A Neuro-Inspired Autoencoding Defense Against Adversarial Attacks", IEEE International Conference on Image Processing (ICIP 2021)
C. Bakiskan, S. Gopalakrishnan, M. Cekic, U. Madhow, R. Pedarsani, "Polarizing Front Ends for Robust CNNs", in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, May 2020.
Soorya Gopalakrishnan*, Metehan Cekic*, Upamanyu Madhow, "Robust Wireless Fingerprinting via Complex-Valued Neural Networks", in IEEE Global Communications Conference (Globecom), Waikoloa, Hawaii, Dec. 2019.
Resume
metehancekic.pdf