activity
20132023
most citedHomomorphic Encryption and Federated Learning based Privacy-Preserving CNN Training: COVID-19 Detection Use-Case

5 citations · 16 across the 18 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2022

Anomaly Detection in Power Markets and Systems

Ugur Halden, Umit Cali, Ferhat Ozgur Catak +2

The widespread use of information and communication technology (ICT) over the course of the last decades has been a primary catalyst behind the digitalization of power systems. Mea…

cs.LG2022★ 1 cited

Hybrid AI-based Anomaly Detection Model using Phasor Measurement Unit Data

Yuval Abraham Regev, Henrik Vassdal, Ugur Halden +2

Over the last few decades, extensive use of information and communication technologies has been the main driver of the digitalization of power systems. Proper and secure monitoring…

cs.LG2022

Unreasonable Effectiveness of Last Hidden Layer Activations for Adversarial Robustness

Omer Faruk Tuna, Ferhat Ozgur Catak, M. Taner Eskil

In standard Deep Neural Network (DNN) based classifiers, the general convention is to omit the activation function in the last (output) layer and directly apply the softmax functio…

cs.LG2021★ 1 cited

Adversarial Machine Learning Security Problems for 6G: mmWave Beam Prediction Use-Case

Evren Catak, Ferhat Ozgur Catak, Arild Moldsvor

6G is the next generation for the communication systems. In recent years, machine learning algorithms have been applied widely in various fields such as health, transportation, and…

cs.LG2021★ 1 cited

Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples

Omer Faruk Tuna, Ferhat Ozgur Catak, M. Taner Eskil

Deep neural network architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully cra…

cs.LG2020

Closeness and Uncertainty Aware Adversarial Examples Detection in Adversarial Machine Learning

Omer Faruk Tuna, Ferhat Ozgur Catak, M. Taner Eskil

While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to delibera…