Undermining deep learning based channel estimation via adversarial wireless signal fabrication

T Hou, T Wang, Z Lu, Y Liu, Y Sagduyu - … of the 2022 ACM Workshop on …, 2022 - dl.acm.org
Channel estimation is a crucial step in wireless communications. The estimator identifies the
wireless channel distortions during the signal propagation and this information is further …

Adversarial Attacks on LoRa Device Identification and Rogue Signal Detection with Deep Learning

YE Sagduyu, T Erpek - MILCOM 2023-2023 IEEE Military …, 2023 - ieeexplore.ieee.org
Low-Power Wide-Area Network (LPWAN) technologies, such as LoRa, have gained
significant attention for their ability to enable long-range, low-power communication for …

Adversarial jamming attacks and defense strategies via adaptive deep reinforcement learning

F Wang, C Zhong, MC Gursoy, S Velipasalar - arXiv preprint arXiv …, 2020 - arxiv.org
As the applications of deep reinforcement learning (DRL) in wireless communications grow,
sensitivity of DRL based wireless communication strategies against adversarial attacks has …

Adversarial machine learning for nextg covert communications using multiple antennas

B Kim, Y Sagduyu, K Davaslioglu, T Erpek, S Ulukus - Entropy, 2022 - mdpi.com
This paper studies the privacy of wireless communications from an eavesdropper that
employs a deep learning (DL) classifier to detect transmissions of interest. There exists one …

Adversarial reinforcement learning in dynamic channel access and power control

F Wang, MC Gursoy… - 2021 IEEE Wireless …, 2021 - ieeexplore.ieee.org
Deep reinforcement learning (DRL) has recently been used to perform efficient resource
allocation in wireless communications. In this paper, the vulnerabilities of such DRL agents …

Fight Against Smart Communication Rival: An Intelligent Jamming Approach With Trend-Oriented Efficacy Evaluation

Z Feng, Y Xu, Y Jiao, G Li, W Li… - IEEE Wireless …, 2022 - ieeexplore.ieee.org
This letter investigates a jamming problem in the confrontation scenario when both the
opposites are intelligent. Most existing studies assumed the learning-based jammer could …

Jamming Attacks on NextG Radio Access Network Slicing with Reinforcement Learning

Y Shi, YE Sagduyu, T Erpek… - 2022 IEEE Future …, 2022 - ieeexplore.ieee.org
This paper studies how to launch an attack on reinforcement learning for network slicing in
NextG radio access network (RAN). An adversarial machine learning approach is pursued to …

Adversarial machine learning and defense game for NextG signal classification with deep learning

YE Sagduyu - MILCOM 2022-2022 IEEE Military …, 2022 - ieeexplore.ieee.org
This paper presents a game-theoretic framework to study the interactions of attack and
defense for deep learning-based NextG signal classification. NextG systems such as the one …

Resilient dynamic channel access via robust deep reinforcement learning

F Wang, C Zhong, MC Gursoy, S Velipasalar - IEEE Access, 2021 - ieeexplore.ieee.org
As the applications of deep reinforcement learning (DRL) in wireless communications grow,
sensitivity of DRL-based wireless communication strategies against adversarial attacks has …

Jamming attacks on decentralized federated learning in general multi-hop wireless networks

Y Shi, YE Sagduyu, T Erpek - IEEE INFOCOM 2023-IEEE …, 2023 - ieeexplore.ieee.org
Decentralized federated learning (DFL) is an ef-fective approach to train a deep learning
model at multiple nodes over a multi-hop network, without the need of a server having direct …