output
20162022
most citedMachine Learning in NextG Networks via Generative Adversarial Networks

58 citations

Showing eess.SPShow all

7 papers · 1 filter

eess.SP2021★ 3 cited

Adversarial Attacks on Deep Learning Based mmWave Beam Prediction in 5G and Beyond

Brian Kim, Yalin E. Sagduyu, Tugba Erpek +1

Deep learning provides powerful means to learn from spectrum data and solve complex tasks in 5G and beyond such as beam selection for initial access (IA) in mmWave communications.…

eess.SP2020★ 3 cited

Adversarial Attacks with Multiple Antennas Against Deep Learning-Based Modulation Classifiers

Brian Kim, Yalin E. Sagduyu, Tugba Erpek +2

We consider a wireless communication system, where a transmitter sends signals to a receiver with different modulation types while the receiver classifies the modulation types of t…

eess.SP2020★ 3 cited

Adversarial Machine Learning based Partial-model Attack in IoT

Zhengping Luo, Shangqing Zhao, Zhuo Lu +2

As Internet of Things (IoT) has emerged as the next logical stage of the Internet, it has become imperative to understand the vulnerabilities of the IoT systems when supporting div…

eess.SP2020★ 1 cited

Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifiers

Yi Shi, Kemal Davaslioglu, Yalin E. Sagduyu

This paper presents how to leak private information from a wireless signal classifier by launching an over-the-air membership inference attack (MIA). As machine learning (ML) algor…

eess.SP2020

Fast Initial Access with Deep Learning for Beam Prediction in 5G mmWave Networks

Tarun S. Cousik, Vijay K. Shah, Jeffrey H. Reed +2

This paper presents DeepIA, a deep learning solution for faster and more accurate initial access (IA) in 5G millimeter wave (mmWave) networks when compared to conventional IA. By u…

eess.SP2020★ 11 cited

How to Make 5G Communications "Invisible": Adversarial Machine Learning for Wireless Privacy

Brian Kim, Yalin E. Sagduyu, Kemal Davaslioglu +2

We consider the problem of hiding wireless communications from an eavesdropper that employs a deep learning (DL) classifier to detect whether any transmission of interest is presen…