Brian Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Brian Kim has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Azuka Chiejina
Electrical and Computer Engineering, George Mason University, Fairfax, Virginia, United States
1 shared publication - Kaushik Chowdhury
The University of Texas at Austin
1 shared publication Kemal Davaslioglu
Intelligent Automation, a BlueHalo Company, Rockville, MD, USA
1 shared publication- Sennur Ulukus
Department of Electrical and Computer Engineering, University of Maryland, College Park, MD 20742, USA
1 shared publication - Tugba Erpek
Nexcepta, Gaithersburg, MD, USA
1 shared publication - Vijay K. Shah
North Carolina State University, Raleigh, NC, USA
1 shared publication
Latest Publications
- Open Access
- 27 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 237-247
System-level Analysis of Adversarial Attacks and Defenses on Intelligence in O-RAN based Cellular Networks
- 27 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 237-247
Open AccessSystem-level Analysis of Adversarial Attacks and Defenses on Intelligence in O-RAN based Cellular Networks
- Top Cited Papers
- 9 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 21 (6) , 3868-3880
Channel-Aware Adversarial Attacks Against Deep Learning-Based Wireless Signal Classifiers
This paper presents channel-aware adversarial attacks against deep learning-based wireless signal classifiers. There is a transmitter that transmits signals with different modulation types. A deep neural network is used at each receiver to classify its over-the-air received signals to modulation types. In the meantime, an adversary transmits an adversarial perturbation (subject to a power budget) to fool receivers into making errors in classifying signals that are received as superpositions of transmitted signals and adversarial perturbations. First, these evasion attacks are shown to fail when channels are not considered in designing adversarial perturbations. Then, realistic attacks are presented by considering channel effects from the adversary to each receiver. After showing that a channel-aware attack is selective (i.e., it affects only the receiver whose channel is considered in the perturbation design), a broadcast adversarial attack is presented by crafting a common adversarial perturbation to simultaneously fool classifiers at different receivers. The major vulnerability of modulation classifiers to over-the-air adversarial attacks is shown by accounting for different levels of information available about the channel, the transmitter input, and the classifier model. Finally, a certified defense based on randomized smoothing that augments training data with noise is introduced to make the modulation classifier robust to adversarial perturbations.
- 9 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 21 (6) , 3868-3880
Top Cited PapersChannel-Aware Adversarial Attacks Against Deep Learning-Based Wireless Signal Classifiers
This paper presents channel-aware adversarial attacks against deep learning-based wireless signal classifiers. There is a transmitter that transmits signals with different modulation types. A deep neural network is used at each receiver to classify its over-the-air received signals to modulation types. In the meantime, an adversary transmits an adversarial perturbation (subject to a power budget) to fool receivers into making errors in classifying signals that are received as superpositions of transmitted signals and adversarial perturbations. First, these evasion attacks are shown to fail when channels are not considered in designing adversarial perturbations. Then, realistic attacks are presented by considering channel effects from the adversary to each receiver. After showing that a channel-aware attack is selective (i.e., it affects only the receiver whose channel is considered in the perturbation design), a broadcast adversarial attack is presented by crafting a common adversarial perturbation to simultaneously fool classifiers at different receivers. The major vulnerability of modulation classifiers to over-the-air adversarial attacks is shown by accounting for different levels of information available about the channel, the transmitter input, and the classifier model. Finally, a certified defense based on randomized smoothing that augments training data with noise is introduced to make the modulation classifier robust to adversarial perturbations.