Physical Adversarial Attacks Against End-to-End Autoencoder Communication Systems

We show that end-to-end learning of communication systems through deep neural network autoencoders can be extremely vulnerable to physical adversarial attacks. Specifically, we elaborate how an attacker can craft effective physical black-box adversarial attacks. Due to the openness (broadcast nature...

Full description

Saved in:
Bibliographic Details
Published in:IEEE communications letters 2019-05, Vol.23 (5), p.847-850
Main Authors: Sadeghi, Meysam, Larsson, Erik G.
Format: Article
Language:English
Subjects:
Adversarial attacks
Artificial neural networks
autoencoder systems
Communications systems
Decoding
deep learning
end-to-end learning
Jamming
Perturbation
Perturbation methods
Receivers
Transmitters
Wireless communication
wireless security
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We show that end-to-end learning of communication systems through deep neural network autoencoders can be extremely vulnerable to physical adversarial attacks. Specifically, we elaborate how an attacker can craft effective physical black-box adversarial attacks. Due to the openness (broadcast nature) of the wireless channel, an adversary transmitter can increase the block-error-rate of a communication system by orders of magnitude by transmitting a well-designed perturbation signal over the channel. We reveal that the adversarial attacks are more destructive than the jamming attacks. We also show that classical coding schemes are more robust than the autoencoders against both adversarial and jamming attacks.
ISSN:1089-7798
1558-2558
1558-2558
DOI:10.1109/LCOMM.2019.2901469