Adversarial machine learning in wireless communications using RF data: A review

D Adesina, CC Hsieh, YE Sagduyu… - … Surveys & Tutorials, 2022 - ieeexplore.ieee.org
Machine learning (ML) provides effective means to learn from spectrum data and solve
complex tasks involved in wireless communications. Supported by recent advances in …

Channel-aware adversarial attacks against deep learning-based wireless signal classifiers

B Kim, YE Sagduyu, K Davaslioglu… - IEEE Transactions …, 2021 - ieeexplore.ieee.org
This paper presents channel-aware adversarial attacks against deep learning-based
wireless signal classifiers. There is a transmitter that transmits signals with different …

Adversarial machine learning for 5G communications security

YE Sagduyu, T Erpek, Y Shi - Game Theory and Machine …, 2021 - Wiley Online Library
Machine learning provides automated means to capture complex dynamics of wireless
spectrum and support better understanding of spectrum resources and their efficient …

[HTML][HTML] Exploring practical vulnerabilities of machine learning-based wireless systems

Z Liu, C Xu, Y Xie, E Sie, F Yang, K Karwaski… - … USENIX Symposium on …, 2023 - usenix.org
NSDI '23 Technical Sessions | USENIX Sign In Conferences Attend Registration Information
Registration Discounts Grant Opportunities Venue, Hotel, and Travel Program Technical …

Adversarial machine learning for flooding attacks on 5G radio access network slicing

Y Shi, YE Sagduyu - 2021 IEEE International Conference on …, 2021 - ieeexplore.ieee.org
Network slicing manages network resources as virtual resource blocks (RBs) for the 5G
Radio Access Network (RAN). Each communication request comes with quality of …

Membership inference attack and defense for wireless signal classifiers with deep learning

Y Shi, YE Sagduyu - IEEE Transactions on Mobile Computing, 2022 - ieeexplore.ieee.org
An over-the-air membership inference attack (MIA) is presented to leak private information
from a wireless signal classifier. Machine learning (ML) provides powerful means to classify …

Adversarial attacks against deep learning based power control in wireless communications

B Kim, Y Shi, YE Sagduyu, T Erpek… - 2021 IEEE Globecom …, 2021 - ieeexplore.ieee.org
We consider adversarial machine learning based attacks on power allocation where the
base station (BS) allocates its transmit power to multiple orthogonal subcarriers by using a …

Adversarial attacks on deep learning based mmWave beam prediction in 5G and beyond

B Kim, Y Sagduyu, T Erpek… - 2021 IEEE Statistical …, 2021 - ieeexplore.ieee.org
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 …

How to Attack and Defend NextG Radio Access Network Slicing with Reinforcement Learning

Y Shi, YE Sagduyu, T Erpek, MC Gursoy - arXiv preprint arXiv:2101.05768, 2021 - arxiv.org
In this paper, reinforcement learning (RL) for network slicing is considered in NextG radio
access networks, where the base station (gNodeB) allocates resource blocks (RBs) to the …

Channel-Robust Class-Universal Spectrum-Focused Frequency Adversarial Attacks on Modulated Classification Models

S Zhang, J Fu, J Yu, H Xu, H Zha… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
With the improvement of basic designs and the evolution of key algorithms, artificial
intelligence (AI) has been considered by both industry and academia as the most promising …