Corpus ID: 237532326

Adversarial Attacks against Deep Learning Based Power Control in Wireless Communications

  title={Adversarial Attacks against Deep Learning Based Power Control in Wireless Communications},
  author={Brian Kim and Yi Shi and Yalin Evren Sagduyu and Tugba Erpek and Sennur Ulukus},
  • Brian Kim, Yi Shi, +2 authors S. Ulukus
  • Published 16 September 2021
  • Computer Science, Engineering, Mathematics
  • ArXiv
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 deep neural network (DNN) to serve multiple user equipments (UEs). The DNN that corresponds to a regression model is trained with channel gains as the input and returns transmit powers as the output. While the BS allocates the transmit powers to the UEs to maximize rates for all UEs, there is an adversary that aims to… Expand

Figures and Tables from this paper


Adversarial Attacks on Deep Learning Based Power Allocation in a Massive MIMO Network
It is shown that adversarial attacks can break DL-based power allocation in the downlink of a massive multiple-input-multiple-output (maMIMO) network. Expand
Adversarial Attacks with Multiple Antennas Against Deep Learning-Based Modulation Classifiers
An attack to transmit the adversarial perturbation through the channel with the largest channel gain at the symbol level is introduced and it is shown that this attack reduces the classifier accuracy significantly compared to other attacks under different channel conditions in terms of channel variance and channel correlation across antennas. Expand
How to Make 5G Communications "Invisible": Adversarial Machine Learning for Wireless Privacy
The results show that signals with different modulation types and eventually 5G communications can be effectively hidden from an eavesdropper even if it is equipped with a DL classifier to detect transmissions. Expand
Adversarial Deep Learning for Cognitive Radio Security: Jamming Attack and Defense Strategies
A defense scheme is developed against adversarial deep learning by exploiting the sensitivity of deep learning to training errors and allows the transmitter to sustain its performance against intelligent jamming attacks. Expand
Adversarial Attacks on Deep Learning Based mmWave Beam Prediction in 5G And Beyond
This work presents an adversarial attack by generating adversarial perturbations to manipulate the over-the-air captured RSSs as the input to the deep neural network, which reduces the IA performance significantly and fools the DNN into choosing the beams with small RSSs compared to jamming attacks with Gaussian or uniform noise. Expand
Adversarial Machine Learning for 5G Communications Security
To sustain the 5G system operations in the presence of adversaries, a defense mechanism is presented to increase the uncertainty of the adversary in training the surrogate model used for launching its subsequent attacks. Expand
Deep Learning for Launching and Mitigating Wireless Jamming Attacks
  • T. Erpek, Y. Sagduyu, Yi Shi
  • Computer Science, Mathematics
  • IEEE Transactions on Cognitive Communications and Networking
  • 2019
An adversarial machine learning approach is introduced to launch jamming attacks on wireless communications and a defense strategy is presented, where the transmitter systematically selects when to take wrong actions and adapts the level of defense to mislead the jammer into making prediction errors and consequently increase its throughput. Expand
Evaluating Adversarial Evasion Attacks in the Context of Wireless Communications
The current work develops a methodology for evaluating adversarial success in the context of wireless communications, where the primary metric of interest is bit error rate and not human perception, as is the case in image recognition. Expand
Adversarial Deep Learning for Over-the-Air Spectrum Poisoning Attacks
An adversarial deep learning approach is presented to launch over-the-air spectrum poisoning attacks that are energy efficient and hard to detect compared to jamming the long data transmission period, and substantially reduce the throughput. Expand
Spectrum Data Poisoning with Adversarial Deep Learning
This paper considers the case that a cognitive transmitter senses the spectrum and transmits on idle channels determined by a machine learning algorithm and presents an adversarial machine learning approach to launch a spectrum data poisoning attack. Expand